INDEX

Explanations

verbs related to actions or operations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating confusion or misunderstanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 neighb

-0.82

 lifes

-0.78

 ability

-0.76

 probation

-0.75

 wire

-0.75

 prosec

-0.74

 carriage

-0.74

 waterfall

-0.74

 negoti

-0.73

bid

-0.71

POSITIVE LOGITS

Consider

1.56

Whether

1.43

Specifically

1.39

According

1.39

Advertisements

1.38

Indeed

1.36

Advertisement

1.33

For

1.31

Instead

1.31

Because

1.30

Activations Density 0.626%

verbs related to actions or operations

phrases indicating confusion or misunderstanding

No Comments

No Known Activations