INDEX

Explanations

phrases related to legal actions or consequences

oai_token-act-pair · gpt-3.5-turbo

the character "ľ" in various contexts throughout the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 apes

-0.76

 reflex

-0.71

 Mirage

-0.68

 clones

-0.65

 pleasures

-0.64

 clitor

-0.63

 Patriarch

-0.63

 mounts

-0.63

 condem

-0.63

 steps

-0.62

POSITIVE LOGITS

ï¸ı

1.13

ternity

0.97

\-

0.88

uthor

0.87

0.85

âĶĢâĶĢ

0.85

ACP

0.84

oil

0.81

vernment

0.78

amily

0.77

Activations Density 0.203%

phrases related to legal actions or consequences

the character "ľ" in various contexts throughout the text

No Comments

No Known Activations