INDEX

Explanations

phrases emphasizing significant quantities or strengths

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

ysc

-0.74

uay

-0.72

rick

-0.70

 Origins

-0.70

flies

-0.70

 Annotations

-0.68

runs

-0.65

\/\/

-0.64

np

-0.64

\<

-0.64

POSITIVE LOGITS

 thing

1.23

 scenario

1.04

 situation

0.95

 feat

0.90

 delicate

0.89

 drastic

0.87

 huge

0.86

 sensitive

0.86

 hypothetical

0.85

 possibility

0.82

Activations Density 0.026%

phrases emphasizing significant quantities or strengths

No Comments

No Known Activations