INDEX

Explanations

proper nouns or names, particularly the name "Liz"

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 sleeper

-0.85

 sidx

-0.82

xual

-0.76

ierrez

-0.71

CLASSIFIED

-0.70

tesque

-0.68

icted

-0.68

 convict

-0.68

PDATE

-0.67

icts

-0.67

POSITIVE LOGITS

Anne

0.90

 Cheney

0.89

 Anne

0.88

 Lerner

0.86

 Louise

0.84

anie

0.82

Bei

0.80

abel

0.80

otte

0.80

 Nicole

0.79

Activations Density 0.040%

proper nouns or names, particularly the name "Liz"

No Comments

No Known Activations