INDEX

Explanations

references to numerical rankings/orders

oai_token-act-pair · gpt-3.5-turbo

sentences with ranking or scoring information

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gypt

-0.77

 herds

-0.77

 bunny

-0.73

issance

-0.69

 toile

-0.69

 transact

-0.68

 unravel

-0.67

isine

-0.63

 rabbit

-0.63

bir

-0.61

POSITIVE LOGITS

eous

0.84

 whatsoever

0.77

gov

0.75

 Accessed

0.74

CLASSIFIED

0.73

ificant

0.69

Downloadha

0.69

Org

0.69

 Ranking

0.68

RFC

0.67

Activations Density 0.043%

references to numerical rankings/orders

sentences with ranking or scoring information

No Comments

No Known Activations