INDEX

Explanations

detailed and in-depth descriptions

oai_token-act-pair · gpt-3.5-turbo

mentions of detailed descriptions or intricate explanations

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

rament

-0.66

illin

-0.62

isites

-0.60

 Continent

-0.60

cknowled

-0.59

aren

-0.58

erd

-0.58

Ole

-0.58

illard

-0.56

 itch

-0.56

POSITIVE LOGITS

bows

0.81

 fashion

0.72

 form

0.70

 manner

0.67

 mode

0.66

 ILCS

0.65

 guise

0.65

atters

0.63

 srfAttach

0.61

 format

0.61

Activations Density 0.155%

detailed and in-depth descriptions

mentions of detailed descriptions or intricate explanations

No Comments

No Known Activations