INDEX

Explanations

words related to evasion or avoidance, particularly in a legal or criminal context

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

Kind

-0.70

rooms

-0.68

warm

-0.66

bleacher

-0.66

oom

-0.65

cakes

-0.64

mor

-0.64

ãĥī

-0.63

Sad

-0.62

killer

-0.61

POSITIVE LOGITS

 detection

1.31

 FOIA

0.97

 subpoena

0.92

 taxes

0.90

 taxation

0.89

 scrutiny

0.86

 disclosure

0.86

 DMCA

0.86

 waivers

0.86

 prosecution

0.83

Activations Density 0.114%

words related to evasion or avoidance, particularly in a legal or criminal context

No Comments

No Known Activations