INDEX

Explanations

references to microphones

oai_token-act-pair · gpt-3.5-turbo

mentions of microphones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Lod

-0.76

 Arbor

-0.72

 Kinnikuman

-0.72

 Verd

-0.68

 Gardens

-0.68

 Windsor

-0.66

Lv

-0.66

Hur

-0.65

 Burton

-0.65

 Blossom

-0.65

POSITIVE LOGITS

mic

4.15

 microphone

2.49

 microphones

2.03

mic

2.01

Mic

1.73

Mic

1.57

MIC

1.44

MIC

1.32

meg

1.22

micro

1.14

Activations Density 0.013%

references to microphones

mentions of microphones

No Comments

No Known Activations