INDEX

Explanations

information or instructions within a text

oai_token-act-pair · gpt-3.5-turbo

phrases indicating instructions or requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Pinterest

-0.79

cigarettes

-0.78

 Shutterstock

-0.75

existent

-0.74

"—

-0.73

iru

-0.69

livion

-0.69

cigarette

-0.68

 ditch

-0.68

NetMessage

-0.68

POSITIVE LOGITS

itialized

0.88

sequently

0.87

quartered

0.78

 additionally

0.77

Previously

0.75

 Previously

0.72

sequent

0.71

 Details

0.71

 Topic

0.70

cknowled

0.70

Activations Density 0.526%

information or instructions within a text

phrases indicating instructions or requests

No Comments

No Known Activations