INDEX

Explanations

phrases indicating political actions or developments

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

('

-0.72

 perished

-0.67

 ignor

-0.65

 sacrific

-0.62

wra

-0.62

 possessed

-0.61

 murdered

-0.61

 annihil

-0.61

 substituted

-0.61

 murdering

-0.61

POSITIVE LOGITS

 contentious

0.74

 Duterte

0.71

 Lauder

0.71

 prompted

0.70

 bullish

0.68

 bipartisan

0.67

ktop

0.67

plom

0.66

 Canaver

0.66

 Beir

0.66

Activations Density 0.388%

phrases indicating political actions or developments

No Comments

No Known Activations