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

ply

-0.80

iliated

-0.72

placed

-0.72

osponsors

-0.70

heartedly

-0.70

hearted

-0.70

scrib

-0.70

 counsel

-0.70

essen

-0.68

steam

-0.66

POSITIVE LOGITS

 UNITED

0.76

Fas

0.73

MID

0.72

SAN

0.69

ragon

0.68

PIT

0.67

 Corpus

0.66

 Avalon

0.66

âĵĺ

0.66

Bay

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.