INDEX

Explanations

mentions or references to "the American people."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inventoryQuantity

-1.01

catentry

-0.92

Smith

-0.76

ENC

-0.76

Reloaded

-0.75

Prev

-0.74

 Collider

-0.71

Ha

-0.68

SourceFile

-0.66

Sports

-0.65

POSITIVE LOGITS

hood

1.09

 uprising

0.89

folk

0.83

 revolt

0.83

 electing

0.83

orate

0.80

 revol

0.80

 united

0.76

 democratically

0.76

 peacefully

0.76

Activations Density 0.053%

mentions or references to "the American people."

No Comments

No Known Activations