INDEX

Explanations

pronouns referring to a specific entity

oai_token-act-pair · gpt-3.5-turbo

the word "it" and various references to its use in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

tones

-0.67

TED

-0.63

idth

-0.63

ect

-0.62

igmatic

-0.60

itaire

-0.60

telling

-0.59

entary

-0.58

 Toast

-0.58

 Electrical

-0.58

POSITIVE LOGITS

self

1.01

's

0.99

alian

0.99

asca

0.93

chy

0.91

anium

0.90

 publishes

0.88

unes

0.88

 owns

0.87

 employs

0.84

Activations Density 0.256%

pronouns referring to a specific entity

the word "it" and various references to its use in different contexts

No Comments

No Known Activations