INDEX

Explanations

specific terms related to software development issues or fixes

oai_token-act-pair · gpt-3.5-turbo

negative sentiments or phrases indicating loss or lack

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

SPONSORED

-0.83

operation

-0.77

 endeavor

-0.75

ankind

-0.73

successfully

-0.73

 nonetheless

-0.72

founded

-0.72

 humankind

-0.72

orld

-0.71

reality

-0.71

POSITIVE LOGITS

 typo

0.80

 comma

0.78

 respawn

0.77

 unused

0.75

 subtitles

0.74

 parentheses

0.73

 placeholder

0.73

 toggle

0.72

"+

0.71

 spacing

0.71

Activations Density 0.696%

specific terms related to software development issues or fixes

negative sentiments or phrases indicating loss or lack

No Comments

No Known Activations