INDEX

Explanations

significant names or terms related to influential individuals or entities

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

 Vaugh

-0.74

aciously

-0.74

asma

-0.71

ADRA

-0.69

 Ambro

-0.67

 Surviv

-0.66

uates

-0.65

ews

-0.63

itely

-0.63

 PHOTO

-0.62

POSITIVE LOGITS

weed

0.86

*/(

0.85

hoe

0.82

hole

0.81

lein

0.81

loo

0.79

pad

0.77

butt

0.74

stroke

0.73

word

0.72

Activations Density 0.009%

significant names or terms related to influential individuals or entities

No Comments

No Known Activations