INDEX

Explanations

abbreviations and acronyms related to various organizations and 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

pheus

-0.79

andre

-0.74

adian

-0.74

byss

-0.73

atography

-0.72

antha

-0.72

adic

-0.69

andra

-0.66

opus

-0.66

phis

-0.64

POSITIVE LOGITS

actory

1.20

rost

0.89

inity

0.83

owler

0.83

ornia

0.82

rozen

0.81

GF

0.79

estival

0.79

erent

0.79

ONT

0.78

Activations Density 0.019%

abbreviations and acronyms related to various organizations and entities

No Comments

No Known Activations