INDEX

Explanations

reasons or justifications for certain actions or beliefs

oai_token-act-pair · gpt-3.5-turbo

phrases indicating reasons or justifications

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

ologies

-0.69

quickShipAvailable

-0.66

 Appears

-0.65

ches

-0.65

 Blitz

-0.64

ONSORED

-0.64

IDS

-0.63

 Laksh

-0.63

thumbnails

-0.62

lets

-0.61

POSITIVE LOGITS

 believe

1.10

 doubt

1.05

 revisit

1.00

 distrust

0.99

 mistrust

0.97

 disbel

0.93

 celebrate

0.91

 consider

0.89

 rejoice

0.89

 dislike

0.88

Activations Density 0.083%

reasons or justifications for certain actions or beliefs

phrases indicating reasons or justifications

No Comments

No Known Activations