INDEX

Explanations

links or calls to action within texts

oai_token-act-pair · gpt-3.5-turbo

calls to action and links to external content

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

oken

-0.81

·

-0.76

´

-0.74

Ĥª

-0.73

ģ«

-0.72

roots

-0.70

Ń·

-0.68

©

-0.66

ĪĴ

-0.65

dimension

-0.65

POSITIVE LOGITS

 link

1.08

 links

0.89

 embed

0.84

 LINK

0.77

Haf

0.72

 click

0.71

 linked

0.70

 Mehran

0.70

Newsletter

0.70

 Scrib

0.70

Activations Density 0.196%

links or calls to action within texts

calls to action and links to external content

No Comments

No Known Activations