INDEX

Explanations

mentions of the word "Mother" at varying levels of prominence in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Mother" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aneously

-0.75

 compr

-0.70

ahime

-0.69

ramer

-0.69

 mentally

-0.66

 WATCHED

-0.66

sed

-0.65

ript

-0.64

aped

-0.62

chnology

-0.62

POSITIVE LOGITS

 Teresa

1.06

ship

1.04

fuck

1.00

 Nature

0.96

boards

0.95

board

0.93

 Theresa

0.89

hood

0.88

 Goose

0.86

ships

0.82

Activations Density 0.032%

mentions of the word "Mother" at varying levels of prominence in the text

mentions of the term "Mother" in various contexts

No Comments

No Known Activations