INDEX

Explanations

words related to the concept of 'self'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "self" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flags

-0.81

 Rabbit

-0.72

 Powers

-0.72

 Decay

-0.68

 Pose

-0.68

Shot

-0.66

 Crus

-0.64

 Paradise

-0.63

 Canary

-0.63

 Barrier

-0.62

POSITIVE LOGITS

actory

1.09

onso

1.01

rint

0.99

lf

0.97

ibrary

0.96

enn

0.92

 bour

0.91

poons

0.89

andom

0.89

ood

0.89

Activations Density 0.007%

words related to the concept of 'self'

instances of the word "self" in different contexts

No Comments

No Known Activations