INDEX

Explanations

phrases indicating a clear statement or declaration

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing clarity or making something explicit

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

ickle

-0.65

Luck

-0.65

 luck

-0.64

gins

-0.62

 Derby

-0.62

ools

-0.61

apter

-0.59

 Variant

-0.59

lymp

-0.59

otin

-0.58

POSITIVE LOGITS

 explicitly

0.84

 unamb

0.83

 upfront

0.83

 unequivocally

0.82

 emphatically

0.81

ances

0.78

 commitments

0.77

 unequiv

0.77

 plainly

0.75

 distinction

0.74

Activations Density 0.137%

phrases indicating a clear statement or declaration

phrases emphasizing clarity or making something explicit

No Comments

No Known Activations