INDEX

Explanations

specific mentions of various outlets or organizations

oai_token-act-pair · gpt-3.5-turbo

references to inclusion or examples within various contexts

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

lyak

-0.76

rison

-0.68

 cures

-0.67

ptoms

-0.67

orrow

-0.66

 qualities

-0.64

 conviction

-0.64

*/(

-0.64

iencies

-0.64

ibility

-0.62

POSITIVE LOGITS

Tel

0.70

 ours

0.68

 Christianity

0.66

 Dagger

0.65

 Artemis

0.65

 Barb

0.65

 STATS

0.65

Byz

0.64

ATL

0.63

Dom

0.62

Activations Density 0.232%

specific mentions of various outlets or organizations

references to inclusion or examples within various contexts

No Comments

No Known Activations