INDEX

Explanations

phrases related to freedom or release

oai_token-act-pair · gpt-3.5-turbo

instances of the word "freed" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Grimm

-0.72

 Spokane

-0.69

 Mortal

-0.65

 Hale

-0.64

lihood

-0.64

 Humph

-0.63

WAYS

-0.60

 Commentary

-0.59

 Chemical

-0.59

 Hayward

-0.59

POSITIVE LOGITS

 freed

1.18

 freeing

1.16

ktop

1.16

bies

0.94

 liberated

0.94

selage

0.92

chwitz

0.86

Reviewer

0.86

*=-

0.83

 liberate

0.83

Activations Density 0.010%

phrases related to freedom or release

instances of the word "freed" and its variations

No Comments

No Known Activations