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

rophe

-0.73

rive

-0.69

onial

-0.67

hesive

-0.67

perty

-0.66

 roadside

-0.65

oro

-0.65

vernment

-0.65

Loc

-0.64

actic

-0.64

POSITIVE LOGITS

iors

0.74

 colours

0.74

wcsstore

0.73

 colors

0.66

Bench

0.60

 stripes

0.59

 Saban

0.59

hawks

0.58

gpu

0.58

 Glacier

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.