INDEX

Explanations

negative characterizations or descriptors related to current events, particularly in political contexts

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

Effective

-0.78

 probable

-0.73

 enriched

-0.71

theless

-0.71

 Enhanced

-0.71

imately

-0.70

 certific

-0.69

 authorised

-0.68

 individually

-0.68

 contracted

-0.68

POSITIVE LOGITS

stros

1.03

aunts

0.89

agonist

0.88

anny

0.85

isms

0.84

unker

0.84

asses

0.83

angles

0.83

itty

0.82

otypes

0.81

Activations Density 0.179%

negative characterizations or descriptors related to current events, particularly in political contexts

No Comments

No Known Activations