INDEX

Explanations

references to destruction and safety in the context of conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

omics

-0.79

NAS

-0.76

 arguably

-0.74

 Slate

-0.72

uably

-0.71

 POLITICO

-0.71

 Staples

-0.66

 Competitive

-0.66

centric

-0.65

 millennial

-0.65

POSITIVE LOGITS

 bribe

0.93

 villagers

0.93

 afterwards

0.87

 labou

0.86

 policemen

0.84

 medicines

0.80

 till

0.79

)."

0.79

 practise

0.77

 peasants

0.77

Activations Density 1.402%

references to destruction and safety in the context of conflict

No Comments

No Known Activations