INDEX

Explanations

phrases indicating research findings and published studies

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

 Franch

-0.72

 diseng

-0.71

 caster

-0.69

 Trayvon

-0.66

ostic

-0.66

 semblance

-0.65

 broom

-0.65

 mant

-0.62

gg

-0.61

atism

-0.61

POSITIVE LOGITS

 published

1.08

Explore

1.07

published

1.03

 Published

0.95

 findings

0.90

dx

0.89

 neuroscience

0.89

 scientists

0.88

 biologists

0.87

 Neuroscience

0.87

Activations Density 0.140%

phrases indicating research findings and published studies

No Comments

No Known Activations