INDEX

Explanations

the word "insurgents"

oai_token-act-pair · gpt-3.5-turbo

terminology related to insurgent groups and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

lot

-0.75

Jer

-0.74

 Frozen

-0.74

 Torah

-0.73

 Deck

-0.71

Cos

-0.70

 Pier

-0.70

Touch

-0.70

ce

-0.69

 Comet

-0.69

POSITIVE LOGITS

 insurgents

3.26

 insurgent

2.92

 insurgency

2.79

 insurg

2.19

 insurrection

1.53

 guerrilla

1.47

 Taliban

1.36

 militants

1.29

 Afghans

1.29

 separatists

1.22

Activations Density 0.020%

the word "insurgents"

terminology related to insurgent groups and conflict

No Comments

No Known Activations