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

ikuman

-0.71

 Dign

-0.68

 Akin

-0.67

izophren

-0.65

quartered

-0.64

drawn

-0.62

 pharm

-0.62

 Episcopal

-0.62

XVI

-0.62

 Adinida

-0.61

POSITIVE LOGITS

 Carbuncle

0.76

fw

0.71

##

0.70

VERTISEMENT

0.70

Mach

0.68

duc

0.67

retch

0.65

âĸł

0.63

allas

0.63

efficiency

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.