INDEX

Explanations

proper nouns related to people or organizations

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĪĴ

-0.80

ħĭ

-0.79

aptic

-0.77

gemony

-0.74

ãĤ©

-0.73

etry

-0.72

sterdam

-0.72

ete

-0.71

ĺ

-0.71

ileged

-0.70

POSITIVE LOGITS

aukee

0.77

angelo

0.72

kus

0.72

Pull

0.71

 Hers

0.68

MAN

0.67

 Lans

0.67

hin

0.66

Osc

0.66

Offline

0.65

Activations Density 0.069%

proper nouns related to people or organizations

specific names or terms related to individuals or entities

No Comments

No Known Activations