INDEX

Explanations

quantities or descriptions of items or situations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate quantities or important contributions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

advertising

-0.90

amel

-0.71

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.71

African

-0.68

his

-0.68

ãĥ¼ãĤ¯

-0.68

ser

-0.66

FIL

-0.64

 Ambro

-0.64

ansson

-0.64

POSITIVE LOGITS

 chance

0.95

 opportunity

0.93

 glimpse

0.92

 knack

0.90

 abundance

0.85

 choice

0.83

 tendency

0.79

 feeling

0.78

 shortage

0.77

 reason

0.76

Activations Density 0.258%

quantities or descriptions of items or situations

phrases that indicate quantities or important contributions

No Comments

No Known Activations