INDEX

Explanations

references to objects, entities, or concepts that are distinct from a specific main object or entity

oai_token-act-pair · gpt-3.5-turbo

the recurring theme of "other" in relation to different contexts and categories

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hua

-0.77

hower

-0.74

uca

-0.67

zai

-0.65

hak

-0.63

uterte

-0.63

ettel

-0.63

vg

-0.62

onics

-0.62

atown

-0.62

POSITIVE LOGITS

worldly

1.04

 aspects

0.93

 facets

0.90

 components

0.78

 respects

0.75

 kinds

0.74

 avenues

0.74

 factions

0.73

iating

0.73

 except

0.71

Activations Density 0.034%

references to objects, entities, or concepts that are distinct from a specific main object or entity

the recurring theme of "other" in relation to different contexts and categories

No Comments

No Known Activations