INDEX

Explanations

questions often related to personal opinions or experiences

oai_token-act-pair · gpt-3.5-turbo

questions and statements related to access and concerns regarding health and societal issues

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

itol

-0.72

 Chevron

-0.61

ICLE

-0.60

CCC

-0.60

perties

-0.59

CoC

-0.59

pty

-0.59

 civilized

-0.59

 civilization

-0.59

 Cecil

-0.58

POSITIVE LOGITS

 GOODMAN

0.82

anga

0.69

kamp

0.69

Interview

0.68

laughs

0.67

 studio

0.67

 largeDownload

0.63

 Studio

0.62

 hiatus

0.62

olver

0.62

Activations Density 0.182%

questions often related to personal opinions or experiences

questions and statements related to access and concerns regarding health and societal issues

No Comments

No Known Activations