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

iral

-0.81

romptu

-0.76

ulton

-0.75

 organise

-0.74

inav

-0.69

itionally

-0.68

abul

-0.68

hood

-0.68

ancial

-0.66

 campaigned

-0.65

POSITIVE LOGITS

 hosts

0.67

 Boat

0.65

0.64

iv

0.63

 Knot

0.63

oise

0.63

Phi

0.63

************

0.63

 repl

0.62

\/\/

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.