INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and geographical locations

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

ues

-0.75

ulatory

-0.73

sight

-0.71

ãĤ¡

-0.70

encers

-0.69

ski

-0.69

furt

-0.68

cod

-0.68

ences

-0.67

ICE

-0.67

POSITIVE LOGITS

ysc

0.77

ascus

0.75

è£ħ

0.72

Kod

0.70

mercial

0.68

merce

0.67

chuk

0.67

ickr

0.65

gow

0.64

ħĭ

0.63

Activations Density 0.056%

names of individuals

proper nouns, particularly names and geographical locations

No Comments

No Known Activations