INDEX

Explanations

references to the word "Stone."

oai_token-act-pair · gpt-3.5-turbo

the word "Stone" and its various contexts or associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

oresc

-0.89

orescence

-0.87

ornia

-0.85

merce

-0.83

unct

-0.75

olulu

-0.75

ores

-0.72

achine

-0.71

olitan

-0.69

ership

-0.68

POSITIVE LOGITS

hill

1.00

falls

0.95

castle

0.88

wright

0.87

Stone

0.87

fish

0.85

works

0.84

 stone

0.82

cold

0.81

 Soup

0.81

Activations Density 0.033%

references to the word "Stone."

the word "Stone" and its various contexts or associations

No Comments

No Known Activations