INDEX

Explanations

specific words related to the concept of a "knot."

oai_token-act-pair · gpt-3.5-turbo

references to specific knots and elements associated with them

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

ered

-0.87

face

-0.80

illac

-0.79

iors

-0.77

rums

-0.77

horn

-0.75

 Gutenberg

-0.74

scape

-0.73

rum

-0.71

quet

-0.71

POSITIVE LOGITS

 Lauder

0.86

 ILCS

0.84

abulary

0.83

kowski

0.76

naire

0.76

asso

0.75

velength

0.74

 Leilan

0.73

 seaw

0.72

acies

0.71

Activations Density 0.059%

specific words related to the concept of a "knot."

references to specific knots and elements associated with them

No Comments

No Known Activations