INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 extinguished

-0.66

rid

-0.65

 older

-0.64

 offline

-0.63

ogle

-0.61

 accompl

-0.60

 unfocused

-0.60

marked

-0.60

cking

-0.60

 scheduled

-0.59

POSITIVE LOGITS

utical

0.85

 srfAttach

0.76

FTWARE

0.75

}:

0.74

ãĤĵ

0.72

})

0.71

udeau

0.70

}"

0.69

atan

0.69

 Inspection

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.