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

ucci

-0.77

chenko

-0.76

ertation

-0.74

rise

-0.72

ileaks

-0.70

adelphia

-0.69

psey

-0.69

WN

-0.68

elsen

-0.68

iann

-0.67

POSITIVE LOGITS

 swords

0.65

 rationality

0.64

 Arrows

0.64

 laughs

0.64

bay

0.63

ul

0.62

Lot

0.61

ãĥ¼ãĥĨ

0.61

 corpus

0.60

 sake

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.