INDEX

Explanations

proper nouns related to various locations and organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Retrieved

-0.57

 thereto

-0.57

-0.53

iator

-0.52

SPONSORED

-0.51

NEO

-0.51

 mustache

-0.51

 latter

-0.49

?).

-0.48

%).

-0.47

POSITIVE LOGITS

agar

0.67

anya

0.59

wagon

0.57

 fray

0.57

indal

0.54

aer

0.54

erness

0.53

amiya

0.51

hess

0.51

 limbo

0.51

Activations Density 1.647%

proper nouns related to various locations and organizations

proper nouns and specific locations

No Comments

No Known Activations