INDEX

Explanations

clear and decisive descriptions or statements

oai_token-act-pair · gpt-3.5-turbo

expressions indicating clarity or clearly defined concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

eatures

-0.83

 tremend

-0.83

unte

-0.80

 Loft

-0.74

inse

-0.72

ITAL

-0.72

 nostalg

-0.70

 therap

-0.69

LI

-0.69

uld

-0.67

POSITIVE LOGITS

ances

1.14

ance

0.94

cut

0.92

cuts

0.89

iary

0.87

 sailing

0.81

 clear

0.81

Clear

0.80

 distinction

0.76

 enough

0.76

Activations Density 0.030%

clear and decisive descriptions or statements

expressions indicating clarity or clearly defined concepts

No Comments

No Known Activations