INDEX

Explanations

statements or references to being or existing in a particular state or condition

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

 Hacker

-0.60

MAS

-0.60

 Shall

-0.60

 Sakuya

-0.59

BT

-0.59

ANN

-0.58

Pai

-0.57

 Freem

-0.56

 outlaw

-0.56

POSITIVE LOGITS

 weakest

0.79

inki

0.75

nown

0.73

ezvous

0.73

 safest

0.73

 nearest

0.72

jured

0.71

zel

0.70

lins

0.70

essel

0.69

Activations Density 0.054%

statements or references to being or existing in a particular state or condition

No Comments

No Known Activations