INDEX

Explanations

terms related to expert opinions, testimonies, and witnesses

oai_token-act-pair · gpt-3.5-turbo

mentions of experts in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

apo

-0.73

strip

-0.72

FACE

-0.72

 Mellon

-0.70

rill

-0.67

MET

-0.66

 Yamato

-0.65

 Heroic

-0.63

reath

-0.63

 Shades

-0.62

POSITIVE LOGITS

sonian

0.96

 consulted

0.93

 opinion

0.85

ise

0.85

ieth

0.83

 witness

0.81

icion

0.78

 advise

0.78

inent

0.76

udic

0.76

Activations Density 0.060%

terms related to expert opinions, testimonies, and witnesses

mentions of experts in various fields

No Comments

No Known Activations