INDEX

Explanations

words related to criminal activities and justice

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

pole

-0.74

arity

-0.73

 Pixie

-0.71

rish

-0.71

aeda

-0.68

pora

-0.68

por

-0.66

ioned

-0.66

pread

-0.65

tem

-0.64

POSITIVE LOGITS

ously

0.98

 convictions

0.96

 mastermind

0.95

 punishable

0.91

 victim

0.91

ous

0.91

 spree

0.90

 prosecutions

0.87

 unfocusedRange

0.85

 underworld

0.84

Activations Density 1.981%

words related to criminal activities and justice

No Comments

No Known Activations