INDEX

Explanations

specific phrases or terms that are technical or related to specific events or information

oai_token-act-pair · gpt-3.5-turbo

specific nouns and phrases indicating significant events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Footnote

-0.85

ugi

-0.66

obb

-0.64

ract

-0.62

edes

-0.61

Uncommon

-0.59

ils

-0.57

ãĥ´

-0.57

 Fiber

-0.57

weed

-0.57

POSITIVE LOGITS

at

1.59

at

1.50

At

1.30

At

1.27

atography

1.08

AT

1.02

AT

0.87

ats

0.75

Activations Density 0.251%

specific phrases or terms that are technical or related to specific events or information

specific nouns and phrases indicating significant events or entities

No Comments

No Known Activations