INDEX

Explanations

words related to forensic investigations

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

yip

-0.97

unin

-0.93

idays

-0.77

 Huck

-0.73

spring

-0.72

pins

-0.69

cair

-0.68

eworld

-0.68

Reilly

-0.67

zl

-0.66

POSITIVE LOGITS

 examination

1.06

 analysis

0.98

 investigation

0.94

 biologist

0.92

 examinations

0.90

nsics

0.89

 sciences

0.88

 investigator

0.87

nsic

0.87

 scientist

0.85

Activations Density 0.025%

words related to forensic investigations

No Comments

No Known Activations