INDEX

Explanations

phrases related to numerical series or sequences

oai_token-act-pair · gpt-3.5-turbo

references to series, volumes, or studies

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mp

-0.74

panic

-0.73

comed

-0.73

rop

-0.70

cro

-0.69

uyomi

-0.69

EStreamFrame

-0.65

hat

-0.65

atem

-0.65

kar

-0.64

POSITIVE LOGITS

XII

0.96

XVI

0.95

XIV

0.94

VII

0.93

 VIII

0.86

 XIII

0.84

0.83

Activations Density 0.167%

phrases related to numerical series or sequences

references to series, volumes, or studies

No Comments

No Known Activations