INDEX

Explanations

phrases indicating agreement or consensus

oai_token-act-pair · gpt-3.5-turbo

instances of the word "agreed."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ogging

-0.65

formation

-0.60

ogy

-0.58

chest

-0.58

 blot

-0.57

 Falling

-0.56

 Hast

-0.56

letes

-0.56

ycle

-0.56

Press

-0.56

POSITIVE LOGITS

 agreed

3.50

 agrees

2.19

 agree

2.06

 agreeing

1.97

 disagreed

1.77

 accepted

1.71

 agreement

1.52

 conceded

1.51

 complied

1.48

 negotiated

1.46

Activations Density 0.010%

phrases indicating agreement or consensus

instances of the word "agreed."

No Comments

No Known Activations