INDEX

Explanations

phrases related to video content that the user must watch, often signaling urgency or importance

oai_token-act-pair · gpt-3.5-turbo

references to videos

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 moth

-0.70

 Rutherford

-0.64

arity

-0.64

 Schwarz

-0.63

 stone

-0.63

 wedge

-0.62

 Gibbs

-0.61

 mend

-0.61

 Byrne

-0.61

 consolation

-0.61

POSITIVE LOGITS

 Thumbnails

1.05

 Videos

1.03

 WATCHED

0.93

 Helpful

0.80

olutions

0.79

rities

0.76

illon

0.74

iframe

0.73

Video

0.73

poons

0.73

Activations Density 0.014%

phrases related to video content that the user must watch, often signaling urgency or importance

references to videos

No Comments

No Known Activations