INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

KEN

-0.76

mn

-0.71

ores

-0.70

Corp

-0.70

shield

-0.69

wark

-0.69

LAND

-0.68

ulkan

-0.67

den

-0.67

gd

-0.67

POSITIVE LOGITS

oÄŁ

0.69

 Reincarn

0.68

 broch

0.68

 informational

0.68

 perspect

0.67

 tweaks

0.67

accompan

0.67

ŃĶ

0.66

 Honest

0.66

 pamph

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.