INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

comparisons and contrasts between different subjects or entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 GOODMAN

-0.87

 PLUS

-0.68

 ASAP

-0.62

 contacting

-0.61

 Christy

-0.61

 Proposition

-0.61

 Wrong

-0.61

 doorstep

-0.60

 Brigham

-0.59

 Regist

-0.59

POSITIVE LOGITS

Others

0.72

iliary

0.71

lins

0.70

 others

0.69

empl

0.68

leon

0.67

aughed

0.67

umber

0.66

trak

0.63

ivo

0.62

Activations Density 0.232%

proper nouns

comparisons and contrasts between different subjects or entities

No Known Activations