INDEX

Explanations

the letter "A" in various contexts

oai_token-act-pair · gpt-4o-mini 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

olicy

-0.72

 âĢİ

-0.67

aneously

-0.66

 proceedings

-0.66

 Orient

-0.63

evidence

-0.60

arsity

-0.60

 Everton

-0.59

 Abortion

-0.58

 Exxon

-0.58

POSITIVE LOGITS

cknowled

1.61

cknow

1.54

HAHAHAHA

1.12

verages

1.12

lot

1.07

HHHH

1.05

chieve

1.01

HAHA

1.01

chie

0.99

UTH

0.95

Activations Density 0.154%

the letter "A" in various contexts

No Comments

No Known Activations