INDEX

Explanations

terms related to young people

oai_token-act-pair · gpt-3.5-turbo

mentions of youth and related topics

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

aeda

-0.77

pard

-0.76

ãĤ´ãĥ³

-0.75

ukong

-0.73

uments

-0.70

ertodd

-0.69

igslist

-0.68

ractive

-0.68

ichick

-0.68

rary

-0.67

POSITIVE LOGITS

fulness

1.10

 academy

0.81

 outreach

0.78

ULT

0.78

outh

0.76

fully

0.75

doms

0.75

uates

0.74

bands

0.72

 Scouting

0.70

Activations Density 0.016%

terms related to young people

mentions of youth and related topics

No Comments

No Known Activations