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

Ô

-0.68

 embell

-0.68

 Peters

-0.65

 whistle

-0.63

 showc

-0.61

 proofs

-0.60

ONSORED

-0.60

 Scher

-0.60

 smokes

-0.60

©¶æ

-0.59

POSITIVE LOGITS

igious

0.81

urnal

0.75

ibrarian

0.73

edit

0.72

umblr

0.71

ardless

0.69

ifi

0.68

caster

0.68

atomic

0.68

alties

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.