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

ZX

-0.74

Vs

-0.71

VILLE

-0.71

EVA

-0.70

 Crash

-0.69

IELD

-0.69

VK

-0.69

Esc

-0.68

 Mehran

-0.68

AIR

-0.68

POSITIVE LOGITS

reason

0.90

grain

0.73

isible

0.72

ritical

0.70

ichick

0.70

edition

0.69

 snipp

0.68

pty

0.66

ruciating

0.65

bare

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.