INDEX

Explanations

phrases starting with "Did you" indicating the start of a question being asked

oai_token-act-pair · gpt-3.5-turbo

questions beginning with "Did you" that prompt for information or awareness

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Connector

-0.73

accompan

-0.72

artifacts

-0.71

currently

-0.70

 presently

-0.65

Rel

-0.65

 currently

-0.62

 Frie

-0.61

limits

-0.61

ems

-0.60

POSITIVE LOGITS

 realise

0.90

 mistake

0.86

 notice

0.84

 realize

0.83

 catch

0.82

 miss

0.81

 mention

0.79

 typo

0.77

 originally

0.75

 learn

0.74

Activations Density 0.143%

phrases starting with "Did you" indicating the start of a question being asked

questions beginning with "Did you" that prompt for information or awareness

No Comments

No Known Activations