INDEX

Explanations

No Explanations Found

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

OWS

-0.75

 Burke

-0.69

orr

-0.67

akia

-0.67

=\"

-0.65

NV

-0.63

});

-0.61

±

-0.61

bleacher

-0.60

POSITIVE LOGITS

tons

0.86

 Sprite

0.76

 Anthrop

0.72

ewater

0.68

 newsp

0.68

 mathemat

0.67

pex

0.67

 resil

0.64

cffff

0.64

cos

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.