INDEX

Explanations

references to prominent families associated with conspiracy theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

gap

-0.79

alities

-0.76

opl

-0.72

odic

-0.71

binary

-0.69

ÑĮ

-0.68

anooga

-0.68

ary

-0.67

 experien

-0.67

usterity

-0.66

POSITIVE LOGITS

kefeller

0.89

 Brothers

0.86

 Rockefeller

0.85

enthal

0.84

 Estate

0.81

 Institution

0.79

iets

0.77

 Plaza

0.75

 Syndicate

0.74

 dynasty

0.72

Activations Density 0.002%

references to prominent families associated with conspiracy theories

No Comments

No Known Activations