INDEX

Explanations

terms related to intensity and energy

oai_token-act-pair · gpt-3.5-turbo

mentions of intensity or emphasis in various contexts

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

warts

-0.83

oths

-0.77

aston

-0.77

swick

-0.76

abad

-0.73

fish

-0.71

ordered

-0.70

eston

-0.70

izable

-0.69

roup

-0.69

POSITIVE LOGITS

mble

1.86

ly

0.90

ENSE

0.86

ense

0.81

edly

0.76

lessly

0.75

xual

0.75

 Nunes

0.73

LY

0.70

entimes

0.69

Activations Density 0.047%

terms related to intensity and energy

mentions of intensity or emphasis in various contexts

No Comments

No Known Activations