INDEX

Explanations

dates in the month of July

oai_token-act-pair · gpt-3.5-turbo

dates, specifically in July

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

 cumbers

-0.75

uden

-0.72

inent

-0.71

 unfor

-0.70

andem

-0.69

Interstitial

-0.69

fect

-0.69

 unnecess

-0.68

lac

-0.66

corn

-0.66

POSITIVE LOGITS

nard

0.96

berry

0.88

flower

0.88

 Fourth

0.86

0.84

esville

0.82

ibel

0.82

bug

0.81

0.80

Activations Density 0.019%

dates in the month of July

dates, specifically in July

No Comments

No Known Activations