INDEX

Explanations

company names

oai_token-act-pair · gpt-3.5-turbo

references to companies and their limited liability designations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

BOOK

-0.86

bre

-0.76

FACE

-0.75

\":

-0.72

hyde

-0.70

schild

-0.69

hide

-0.67

bou

-0.67

States

-0.66

filled

-0.64

POSITIVE LOGITS

idents

0.92

iffe

0.91

orporated

0.88

Ltd

0.87

ibaba

0.87

inia

0.83

awar

0.83

isted

0.83

oreal

0.82

iery

0.82

Activations Density 0.013%

company names

references to companies and their limited liability designations

No Comments

No Known Activations