INDEX

Explanations

incidents of conflict or aggression

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

arse

-0.68

quished

-0.68

rontal

-0.67

raltar

-0.66

 Cosponsors

-0.66

ovie

-0.63

ossibility

-0.62

 pione

-0.62

osponsors

-0.60

roxy

-0.60

POSITIVE LOGITS

us

0.90

him

0.86

 theirs

0.80

me

0.77

 them

0.72

 yours

0.69

 hers

0.66

him

0.63

 their

0.63

 ours

0.62

Activations Density 0.355%

incidents of conflict or aggression

No Comments

No Known Activations