INDEX

Explanations

references or mentions of people or places in a text

oai_token-act-pair · gpt-3.5-turbo

phrases indicating citations or references to other statements or sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ieu

-0.77

peat

-0.73

itiz

-0.70

isphere

-0.69

rio

-0.69

HC

-0.69

________________________________________________________________

-0.68

anooga

-0.67

/#

-0.67

iste

-0.67

POSITIVE LOGITS

 incidents

0.76

 situations

0.69

the

0.68

 instances

0.67

 those

0.63

 allegations

0.63

 comments

0.63

 Scenes

0.61

 plural

0.61

 recent

0.61

Activations Density 0.156%

references or mentions of people or places in a text

phrases indicating citations or references to other statements or sources

No Comments

No Known Activations