INDEX

Explanations

phrases related to specific objects or entities

oai_token-act-pair · gpt-3.5-turbo

specific nouns related to various subjects or entities, such as homes, tokens, and medical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 cannabin

-0.88

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.73

etheless

-0.69

AppData

-0.63

,,,,

-0.62

 Helpful

-0.61

ãĤ¤ãĥĪ

-0.61

NCT

-0.60

TextColor

-0.59

 SetTextColor

-0.59

POSITIVE LOGITS

 takeover

1.13

 shootout

0.98

 unveiling

0.97

 outing

0.97

otiation

0.96

yssey

0.95

 invasion

0.93

 trip

0.93

ageddon

0.93

 tour

0.92

Activations Density 0.945%

phrases related to specific objects or entities

specific nouns related to various subjects or entities, such as homes, tokens, and medical terms

No Comments

No Known Activations