INDEX

Explanations

adjectives describing positive qualities or states

oai_token-act-pair · gpt-3.5-turbo

instances of the word "good."

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

 Span

-0.66

 span

-0.63

 offshore

-0.61

 mount

-0.59

ument

-0.58

 accus

-0.58

 blaze

-0.58

 spans

-0.58

 elevation

-0.57

 tens

-0.57

POSITIVE LOGITS

good

3.92

Good

2.14

 GOOD

1.85

 Good

1.68

bad

1.64

better

1.59

 good

1.58

nice

1.40

great

1.27

Excellent

1.25

Activations Density 0.006%

adjectives describing positive qualities or states

instances of the word "good."

No Comments

No Known Activations