INDEX

Explanations

specific actions or events being described

oai_token-act-pair · gpt-3.5-turbo

phrases indicating actions or processes related to rules, regulations, or state changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 successors

-0.71

vin

-0.69

 respectively

-0.68

catentry

-0.67

ortunate

-0.64

FY

-0.64

](

-0.63

sty

-0.62

resents

-0.62

$.

-0.62

POSITIVE LOGITS

 scarce

0.80

 everywhere

0.78

 abound

0.70

 ration

0.69

 Dempsey

0.67

 shortages

0.67

 rife

0.64

 Parenthood

0.63

 Ballard

0.62

 glac

0.62

Activations Density 0.685%

specific actions or events being described

phrases indicating actions or processes related to rules, regulations, or state changes

No Comments

No Known Activations