INDEX

Explanations

short informative sentences or phrases typically found at the beginning or end of text segments

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce lists or breakdowns of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ibles

-0.73

aukee

-0.70

 Ended

-0.67

 afterlife

-0.66

 mattered

-0.66

 underdog

-0.64

 Soon

-0.64

 Surprise

-0.61

Tokens

-0.61

 Weird

-0.61

POSITIVE LOGITS

ographical

0.76

 reproduce

0.73

 excerpt

0.72

 links

0.72

ption

0.72

 excerpts

0.71

 appl

0.70

xual

0.69

rame

0.68

amas

0.68

Activations Density 0.098%

short informative sentences or phrases typically found at the beginning or end of text segments

phrases that introduce lists or breakdowns of information

No Comments

No Known Activations