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

SL

-0.71

RF

-0.69

Sky

-0.67

Rai

-0.67

 Riders

-0.66

ELS

-0.65

chan

-0.64

NRS

-0.63

Drag

-0.63

INA

-0.63

POSITIVE LOGITS

algia

0.71

 decomp

0.70

 CLIENT

0.69

 resp

0.68

 headache

0.68

 diarr

0.66

 stre

0.65

idium

0.63

 smelling

0.63

 glut

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.