INDEX

Explanations

keywords related to operations or processes

oai_token-act-pair · gpt-3.5-turbo

references to operational roles or jobs within a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

USER

-0.73

 skim

-0.71

 marsh

-0.70

theless

-0.70

 vengeance

-0.65

 Ceres

-0.65

 Heller

-0.65

 encountering

-0.64

 spotting

-0.61

 afore

-0.61

POSITIVE LOGITS

ators

1.76

ational

1.70

ating

1.67

ations

1.65

atory

1.53

ator

1.53

atively

1.51

atives

1.47

ative

1.47

ates

1.38

Activations Density 0.037%

keywords related to operations or processes

references to operational roles or jobs within a system

No Comments

No Known Activations