INDEX

Explanations

technical or informational content related to specific topics or entities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate essential information or key points to know about a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

umbn

-0.73

POSE

-0.71

HI

-0.67

DATA

-0.66

qv

-0.66

roximately

-0.66

viation

-0.66

ividual

-0.65

urat

-0.64

represented

-0.62

POSITIVE LOGITS

 myths

0.82

 Replay

0.82

abouts

0.81

 insider

0.76

 lessons

0.76

 pros

0.76

 Lessons

0.73

 Picks

0.72

 tips

0.71

 Questions

0.68

Activations Density 0.690%

technical or informational content related to specific topics or entities

phrases that indicate essential information or key points to know about a topic

No Comments

No Known Activations