INDEX

Explanations

mentions of influential or famous individuals

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

CBI

-0.66

[*]

-0.60

 lodging

-0.59

 Notting

-0.58

 toile

-0.57

Balt

-0.57

 Firm

-0.55

 podium

-0.54

 questioning

-0.53

 AUTHOR

-0.53

POSITIVE LOGITS

intosh

0.93

gage

0.89

ufact

0.87

arella

0.85

waukee

0.82

ogi

0.80

nih

0.79

udi

0.79

nesota

0.79

ashtra

0.77

Activations Density 0.648%

mentions of influential or famous individuals

No Comments

No Known Activations