INDEX

Explanations

references to editorial content or editorials

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tsky

-0.69

JPM

-0.69

ivas

-0.66

ÅĤ

-0.64

igslist

-0.64

adows

-0.62

theless

-0.62

romy

-0.62

azon

-0.61

reek

-0.59

POSITIVE LOGITS

 Picks

0.86

ials

0.86

ãĤ¦ãĤ¹

0.76

letters

0.65

 Newsletter

0.64

ship

0.62

stown

0.62

 subscriptions

0.61

verage

0.60

ustration

0.58

Activations Density 0.003%

references to editorial content or editorials

No Comments

No Known Activations