INDEX

Explanations

mentions of the word "honey" at varying intensities

oai_token-act-pair · gpt-3.5-turbo

references to honey and its various uses or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ative

-0.90

uers

-0.82

osure

-0.80

aneous

-0.78

istical

-0.76

ŃĶ

-0.76

ngth

-0.75

uing

-0.73

ATIONS

-0.73

aneously

-0.72

POSITIVE LOGITS

moon

1.38

bees

1.18

comb

1.08

bee

1.05

bee

0.95

pots

0.95

oney

0.93

bean

0.92

pot

0.89

beans

0.89

Activations Density 0.028%

mentions of the word "honey" at varying intensities

references to honey and its various uses or contexts

No Comments

No Known Activations