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

wed

-0.68

"]

-0.63

ople

-0.63

 Sched

-0.61

dt

-0.60

jong

-0.58

LA

-0.58

angelo

-0.57

 schedule

-0.57

 celebrating

-0.56

POSITIVE LOGITS

 passers

0.71

 robber

0.70

 unlaw

0.70

 eater

0.68

itiz

0.68

weeney

0.67

ngth

0.65

ntil

0.65

Chance

0.65

ĸļ

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.