INDEX

Explanations

proper nouns, particularly names of individuals or locations

oai_token-act-pair · gpt-3.5-turbo

names of individuals and specific terms related to entities or events

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

encing

-0.83

encers

-0.76

ively

-0.75

isions

-0.70

iring

-0.70

apers

-0.69

ision

-0.69

iple

-0.68

ires

-0.68

arily

-0.68

POSITIVE LOGITS

ishop

0.84

wana

0.82

keley

0.81

halla

0.80

hari

0.79

ruary

0.75

achelor

0.75

EGIN

0.75

reath

0.74

axter

0.73

Activations Density 0.130%

proper nouns, particularly names of individuals or locations

names of individuals and specific terms related to entities or events

No Comments

No Known Activations