INDEX

Explanations

references to judicial systems and court rulings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ku

-0.79

wagen

-0.79

 Horus

-0.76

-0.73

ontent

-0.73

 Remem

-0.71

ufact

-0.71

icro

-0.70

pload

-0.70

isable

-0.68

POSITIVE LOGITS

 justices

1.18

Court

1.08

 sided

1.03

 Court

1.01

 appellate

1.00

 Appeals

0.92

 judge

0.91

Judge

0.89

 ruling

0.89

 upholding

0.89

Activations Density 0.048%

references to judicial systems and court rulings

No Comments

No Known Activations