INDEX

Explanations

adjectives and descriptive phrases that convey intensity or evaluation

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'l'

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

 Gaul

-0.71

 Doodle

-0.62

enegger

-0.62

naires

-0.60

 Slug

-0.58

 tabl

-0.57

 Trails

-0.56

 Squirrel

-0.56

 motivations

-0.56

 Decay

-0.56

POSITIVE LOGITS

forth

0.78

ready

0.75

very

0.74

ternity

0.74

treated

0.73

reci

0.72

minecraft

0.71

ished

0.71

cffffcc

0.71

extremely

0.70

Activations Density 0.156%

adjectives and descriptive phrases that convey intensity or evaluation

instances of the letter 'l'

No Comments

No Known Activations