INDEX

Explanations

phrases or sentences indicating belief or thoughts about certain situations or individuals

oai_token-act-pair · gpt-3.5-turbo

expressions that convey beliefs or perceptions about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Decay

-0.63

 Submission

-0.61

 VIDEOS

-0.61

 Invention

-0.57

udeau

-0.55

izo

-0.55

 Subtle

-0.53

STRUCT

-0.53

Newsletter

-0.52

ECK

-0.52

POSITIVE LOGITS

to

0.97

by

0.78

ocry

0.67

 guilty

0.64

 Cosponsors

0.63

 responsible

0.63

 capable

0.62

imately

0.62

 destined

0.61

 competent

0.60

Activations Density 0.092%

phrases or sentences indicating belief or thoughts about certain situations or individuals

expressions that convey beliefs or perceptions about various subjects

No Comments

No Known Activations