INDEX

Explanations

declarative statements followed by a comparison or contrast

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "None."

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

 marking

-0.65

lif

-0.65

 ideal

-0.60

 guys

-0.60

 planners

-0.59

 hips

-0.58

 resear

-0.58

agers

-0.58

 tours

-0.58

rave

-0.58

POSITIVE LOGITS

 None

3.55

None

2.54

none

1.92

 none

1.79

 Nothing

1.59

 Neither

1.34

 NULL

1.32

 False

1.30

Nothing

1.22

TBA

1.18

Activations Density 0.010%

declarative statements followed by a comparison or contrast

occurrences of the word "None."

No Comments

No Known Activations