INDEX

Explanations

references to military and security forces, specifically the National Guard

oai_token-act-pair · gpt-3.5-turbo

references to various types of military or law enforcement guard units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.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

Sov

-0.73

 Craw

-0.70

jad

-0.65

Hop

-0.64

ãĥ´

-0.63

ãĥ£

-0.61

doi

-0.60

other

-0.59

selves

-0.59

Else

-0.58

POSITIVE LOGITS

 Corps

0.91

 stationed

0.88

 uniforms

0.86

naire

0.77

 detachment

0.77

 salute

0.77

iness

0.76

ership

0.76

 Guard

0.75

 disbanded

0.72

Activations Density 0.018%

references to military and security forces, specifically the National Guard

references to various types of military or law enforcement guard units

No Comments

No Known Activations