INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

names and terms associated with specific individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

enment

-0.71

 Scandinavian

-0.70

 Wooden

-0.70

 succession

-0.67

ische

-0.66

 Scandinav

-0.65

ization

-0.64

ously

-0.64

 Sanskrit

-0.63

icity

-0.63

POSITIVE LOGITS

 Fitz

0.93

yip

0.85

metry

0.84

gerald

0.82

intosh

0.80

sonian

0.80

mat

0.78

hered

0.77

match

0.77

ilib

0.77

Activations Density 0.019%

proper nouns

names and terms associated with specific individuals and organizations

No Comments

No Known Activations