INDEX

Explanations

names of individuals or entities, especially focused on criminal activities or suspicious behavior

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

icut

-0.65

theless

-0.62

mouth

-0.61

 Pell

-0.59

 angular

-0.58

 underrated

-0.56

 takeoff

-0.56

 sterling

-0.55

ocular

-0.55

nih

-0.54

POSITIVE LOGITS

cific

0.83

pta

0.81

atchewan

0.81

letal

0.79

nikov

0.78

everal

0.75

ificant

0.73

psons

0.72

å£«

0.70

mbol

0.66

Activations Density 1.538%

names of individuals or entities, especially focused on criminal activities or suspicious behavior

No Comments

No Known Activations