INDEX

Explanations

names and titles of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and significant names in context

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

Spread

-0.79

 ðŁĻĤ

-0.72

Purchase

-0.71

Kids

-0.67

fuck

-0.64

RIP

-0.61

apple

-0.61

 screw

-0.61

advertising

-0.60

âĢ¦

-0.59

POSITIVE LOGITS

plom

0.97

 diplomats

0.90

 briefed

0.84

ideshow

0.82

 Lavrov

0.82

 aides

0.82

 POLITICO

0.81

 spokesman

0.79

 advisers

0.79

 spokeswoman

0.77

Activations Density 0.987%

names and titles of individuals

proper nouns and significant names in context

No Comments

No Known Activations