INDEX

Explanations

mentions of the word "Veterans"

oai_token-act-pair · gpt-3.5-turbo

references to veterans

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

nib

-0.74

åº

-0.72

 pert

-0.69

 knock

-0.68

 binding

-0.68

 coefficients

-0.66

 senses

-0.66

 teasing

-0.65

ree

-0.64

 bund

-0.64

POSITIVE LOGITS

 Veterans

3.94

 Veteran

2.47

Veter

2.17

 veterans

1.81

VA

1.59

 vets

1.41

 Memorial

1.34

 Soldiers

1.33

 Remem

1.21

Vet

1.16

Activations Density 0.010%

mentions of the word "Veterans"

references to veterans

No Comments

No Known Activations