INDEX

Explanations

mentions of microphone or micromanaging in various contexts

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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

tenance

-0.73

 Anonymous

-0.69

vier

-0.66

 Dull

-0.65

 Pact

-0.65

YING

-0.63

 Official

-0.63

ãģĦ

-0.63

ignment

-0.63

 Ultimate

-0.63

POSITIVE LOGITS

ropolitan

1.01

mic

1.01

 microphones

0.97

roman

0.97

 microphone

0.95

romancer

0.92

HAEL

0.89

helle

0.81

rics

0.80

asonic

0.78

Activations Density 0.006%

mentions of microphone or micromanaging in various contexts

mentions of microphones

No Comments

No Known Activations