INDEX

Explanations

phrases related to importance or significance

oai_token-act-pair · gpt-3.5-turbo

the word "important" and its variations in context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bows

-0.79

 Carbuncle

-0.79

ILA

-0.75

á

-0.73

 brim

-0.72

IDES

-0.71

 Fever

-0.71

default

-0.70

ilk

-0.70

fred

-0.70

POSITIVE LOGITS

 proble

0.85

 distingu

0.77

 contributors

0.77

 importance

0.76

 parts

0.76

 portions

0.75

 decisions

0.75

 distinction

0.75

cog

0.74

 aspects

0.73

Activations Density 0.035%

phrases related to importance or significance

the word "important" and its variations in context

No Comments

No Known Activations