INDEX

Explanations

quantitative comparisons indicating a decrease in amount

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fewer."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Draft

-0.88

Mut

-0.74

MO

-0.73

Pros

-0.69

Fight

-0.69

 Immun

-0.68

MD

-0.67

ramid

-0.67

omnia

-0.66

kamp

-0.66

POSITIVE LOGITS

 than

1.31

than

0.90

 Than

0.83

 "$:/

0.80

 digits

0.77

 stringent

0.75

 manageable

0.74

 pesky

0.73

 frequent

0.73

 restrictive

0.71

Activations Density 0.011%

quantitative comparisons indicating a decrease in amount

instances of the word "fewer."

No Comments

No Known Activations