INDEX

Explanations

No Explanations Found

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

ources

-0.80

imens

-0.76

LET

-0.74

":["

-0.72

amine

-0.70

å£

-0.70

'>

-0.70

amines

-0.69

olate

-0.68

Caf

-0.68

POSITIVE LOGITS

 bragging

0.65

 outpost

0.65

 toddlers

0.64

selves

0.63

 approvals

0.62

 accelerator

0.62

flo

0.61

 souls

0.61

college

0.61

 taco

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.