INDEX

Explanations

names of individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

abbreviations or initials of organizations and people

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

 dracon

-0.69

jriwal

-0.62

FORMATION

-0.59

£ı

-0.53

 perfect

-0.51

 surv

-0.50

 subp

-0.50

 carbohyd

-0.50

 podium

-0.50

etheless

-0.49

POSITIVE LOGITS

ich

0.73

uzz

0.73

cia

0.71

oni

0.71

ansky

0.70

ani

0.69

ia

0.68

illo

0.68

nik

0.67

jan

0.67

Activations Density 0.497%

names of individuals or organizations

abbreviations or initials of organizations and people

No Comments

No Known Activations