INDEX

Explanations

proper nouns related to a person named Woods

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Woods."

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

otation

-0.73

LM

-0.70

itia

-0.68

ients

-0.68

utter

-0.67

ially

-0.65

inical

-0.64

ī

-0.64

usions

-0.64

activation

-0.64

POSITIVE LOGITS

hed

1.02

 Hole

0.94

 Woods

0.93

manship

0.90

boro

0.89

enegger

0.88

bury

0.87

schild

0.83

suit

0.81

hole

0.79

Activations Density 0.019%

proper nouns related to a person named Woods

mentions of the name "Woods."

No Comments

No Known Activations