INDEX

Explanations

dates

oai_token-act-pair · gpt-3.5-turbo

dates mentioned in the text

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

Reviewer

-0.84

Interstitial

-0.72

 gifted

-0.70

speaking

-0.68

 thirsty

-0.67

atem

-0.65

 Ital

-0.64

 juggling

-0.64

desc

-0.63

ographed

-0.61

POSITIVE LOGITS

0.90

0.88

0.84

Aug

0.83

onna

0.83

0.81

nard

0.81

Activations Density 0.090%

dates

dates mentioned in the text

No Comments

No Known Activations