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

 cipher

-0.77

iago

-0.74

 scripting

-0.73

 glim

-0.73

duino

-0.72

cester

-0.69

hovah

-0.69

inction

-0.69

emaker

-0.69

 grounding

-0.67

POSITIVE LOGITS

 Provided

0.84

 Quint

0.76

ãĥ³ãĤ¸

0.74

ãĤ¤ãĥĪ

0.74

 Coup

0.73

 Urban

0.73

 Oliv

0.72

 Glob

0.71

 Bout

0.70

 Schwar

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.