INDEX

Explanations

conditional statements indicating potential actions or consequences

oai_token-act-pair · gpt-3.5-turbo

words related to obligation or expectation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

icular

-0.68

oos

-0.64

enda

-0.63

 Peaks

-0.63

ongs

-0.62

endas

-0.62

 commod

-0.61

acus

-0.60

conduct

-0.60

eness

-0.58

POSITIVE LOGITS

 Hover

0.72

terday

0.70

tm

0.65

 November

0.63

Sly

0.63

terms

0.62

 regards

0.61

 Leban

0.61

EMBER

0.61

 Aval

0.61

Activations Density 0.704%

conditional statements indicating potential actions or consequences

words related to obligation or expectation

No Comments

No Known Activations