INDEX

Explanations

words related to interviews and discussions

oai_token-act-pair · gpt-3.5-turbo

discussions and interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ritical

-0.79

uphem

-0.76

coded

-0.73

ItemImage

-0.71

externalActionCode

-0.69

bley

-0.69

ND

-0.68

Ã©n

-0.68

ERROR

-0.67

Tro

-0.67

POSITIVE LOGITS

 topics

1.20

 everything

1.01

why

0.96

how

0.87

 upcoming

0.80

 various

0.80

 overcoming

0.79

 whether

0.79

 whats

0.78

 what

0.78

Activations Density 0.217%

words related to interviews and discussions

discussions and interviews

No Comments

No Known Activations