INDEX

Explanations

terms related to specific subjects such as "movies", "field", "camps", "color", "sanctions", "beer", and "standards"

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

otal

-0.75

akespeare

-0.64

enged

-0.61

vag

-0.60

anuts

-0.59

ealous

-0.58

 assassinated

-0.56

indu

-0.55

athed

-0.54

POSITIVE LOGITS

 arrivals

0.83

 architectures

0.78

 hires

0.77

 additions

0.76

 entrants

0.74

 paradigm

0.74

anding

0.72

stadt

0.70

 iteration

0.70

 technologies

0.69

Activations Density 1.045%

terms related to specific subjects such as "movies", "field", "camps", "color", "sanctions", "beer", and "standards"

No Comments

No Known Activations