INDEX

Explanations

mentions of a specific person, likely someone significant in the context of the document

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

WAYS

-0.74

anwhile

-0.74

xual

-0.72

 Centauri

-0.68

 Fract

-0.62

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.62

 disparate

-0.61

Quotes

-0.61

ulative

-0.61

)=(

-0.61

POSITIVE LOGITS

je

1.08

chester

1.05

ado

1.03

cas

0.99

iane

0.98

idad

0.94

wyn

0.94

sey

0.94

rors

0.93

acles

0.92

Activations Density 0.005%

mentions of a specific person, likely someone significant in the context of the document

No Comments

No Known Activations