INDEX

Explanations

mentions of the name "Perkins" 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_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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

perature

-0.73

aries

-0.71

eworld

-0.69

arily

-0.69

atical

-0.66

plates

-0.64

urgy

-0.62

utable

-0.62

ulatory

-0.62

gencies

-0.61

POSITIVE LOGITS

burgh

0.84

ippi

0.81

nel

0.79

 Perkins

0.78

heim

0.78

burg

0.78

sey

0.76

 Finch

0.74

ervative

0.74

mann

0.73

Activations Density 0.006%

mentions of the name "Perkins" in various contexts

No Comments

No Known Activations