INDEX

Explanations

informational cues or prompts for additional details on various topics

oai_token-act-pair · gpt-3.5-turbo

content that discusses additional information or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 lifeless

-0.69

opped

-0.65

meter

-0.60

odied

-0.60

 imitation

-0.58

 impro

-0.58

 techno

-0.57

 Deliver

-0.56

ĸļ

-0.56

 unden

-0.56

POSITIVE LOGITS

 regarding

0.96

 about

0.87

>>>

0.85

About

0.84

 pertaining

0.82

 ABOUT

0.81

 concerning

0.79

REG

0.79

 About

0.77

 Regarding

0.76

Activations Density 0.057%

informational cues or prompts for additional details on various topics

content that discusses additional information or resources

No Comments

No Known Activations