INDEX

Explanations

keywords related to human health and well-being

oai_token-act-pair · gpt-3.5-turbo

references to health-related topics

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

coni

-0.84

 Helpful

-0.74

 Reloaded

-0.73

 Hundred

-0.69

 Downing

-0.68

Ń·

-0.66

 Albion

-0.65

âĸ¬

-0.65

 Jury

-0.64

 Phant

-0.63

POSITIVE LOGITS

fulness

1.11

care

1.09

span

1.07

iest

1.03

ful

1.03

 care

1.00

ily

0.97

hazard

0.91

conscious

0.91

 professionals

0.86

Activations Density 0.032%

keywords related to human health and well-being

references to health-related topics

No Comments

No Known Activations