INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

possessive forms indicating ownership or association

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

ISO

-0.76

hari

-0.74

lehem

-0.74

linked

-0.73

olkien

-0.72

ENN

-0.72

KT

-0.72

Reviewer

-0.68

":[

-0.65

lling

-0.65

POSITIVE LOGITS

own

1.00

 newest

0.97

 signature

0.92

 footsteps

0.92

 penchant

0.89

 finest

0.89

 insistence

0.87

 whereabouts

0.86

ullivan

0.85

panic

0.85

Activations Density 0.157%

proper nouns

possessive forms indicating ownership or association

No Comments

No Known Activations