INDEX

Explanations

abbreviations or acronyms ending with a period

oai_token-act-pair · gpt-3.5-turbo

specific and frequently repeated abbreviations or acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 advis

-0.77

 stewards

-0.72

 purse

-0.69

 imposition

-0.66

 condem

-0.65

wagen

-0.64

 induct

-0.64

etheless

-0.64

 dictate

-0.63

 leap

-0.63

POSITIVE LOGITS

0.85

Va

0.81

0.77

Skill

0.74

0.73

NET

0.73

 coli

0.73

Activations Density 0.077%

abbreviations or acronyms ending with a period

specific and frequently repeated abbreviations or acronyms

No Comments

No Known Activations