INDEX

Explanations

titles of books and authors

oai_token-act-pair · gpt-3.5-turbo

titles of books and their authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

=\"

-0.78

seys

-0.70

imilar

-0.67

assic

-0.66

 capped

-0.64

devices

-0.64

unts

-0.63

bley

-0.63

fecture

-0.61

 lining

-0.61

POSITIVE LOGITS

 Manifest

0.96

 Strategies

0.96

 Lies

0.92

 Handbook

0.91

 Learned

0.89

 Matters

0.87

 Lessons

0.87

 Diary

0.85

 Politics

0.84

 Revis

0.82

Activations Density 0.316%

titles of books and authors

titles of books and their authors

No Comments

No Known Activations