INDEX

Explanations

references to specific names, titles, and locations

oai_token-act-pair · gpt-3.5-turbo

references to artistic or cultural works and their context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 wallets

-0.68

cause

-0.67

 disabilities

-0.62

spring

-0.60

DEC

-0.60

etheless

-0.59

yak

-0.59

staking

-0.59

Redd

-0.58

 disarm

-0.58

POSITIVE LOGITS

ensis

0.97

osa

0.82

 Noir

0.81

endi

0.79

LLP

0.79

Ã©r

0.78

Ã±o

0.78

igne

0.77

cius

0.76

agne

0.76

Activations Density 0.337%

references to specific names, titles, and locations

references to artistic or cultural works and their context

No Comments

No Known Activations