INDEX

Explanations

references to voting or related concepts

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

 Palestin

-0.73

 Flavoring

-0.72

iasis

-0.68

Kut

-0.66

ahime

-0.65

ptoms

-0.65

 Emer

-0.65

 millenn

-0.65

auga

-0.64

ciating

-0.63

POSITIVE LOGITS

 votes

0.91

 ballots

0.90

vote

0.90

 vote

0.90

 voting

0.87

 Vote

0.84

ndum

0.82

 bloc

0.81

 cast

0.80

 unanimously

0.80

Activations Density 0.492%

references to voting or related concepts

No Comments

No Known Activations