INDEX

Explanations

proper nouns related to famous personalities

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

hips

-0.75

ngth

-0.71

hip

-0.71

atively

-0.71

alid

-0.70

awaru

-0.69

aries

-0.68

los

-0.66

rentices

-0.66

alam

-0.65

POSITIVE LOGITS

 Springer

1.05

 Kramer

0.88

stein

0.78

Fal

0.77

Coy

0.75

 Angelo

0.73

ono

0.72

 Garcia

0.71

 Reese

0.71

ãĤ§

0.71

Activations Density 0.010%

proper nouns related to famous personalities

No Comments

No Known Activations