INDEX

Explanations

the word "body" followed by either a number or an action

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "body."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FEC

-0.66

 Kafka

-0.65

Nex

-0.63

 Dickens

-0.63

 precip

-0.60

 Democr

-0.58

 perfect

-0.57

 Synd

-0.57

 Clover

-0.57

 Griffith

-0.56

POSITIVE LOGITS

body

1.42

guards

1.09

builder

1.00

weight

0.95

bags

0.92

guard

0.90

bag

0.87

building

0.85

anguage

0.84

hood

0.84

Activations Density 0.006%

the word "body" followed by either a number or an action

occurrences of the word "body."

No Comments

No Known Activations