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

 kindly

-0.69

 DEBUG

-0.67

ourage

-0.66

 brave

-0.66

handed

-0.66

ear

-0.65

gotten

-0.65

 gaps

-0.64

ACL

-0.64

 loopholes

-0.64

POSITIVE LOGITS

psc

0.77

Ì¶

0.73

tumblr

0.73

OUP

0.68

JD

0.67

 Mond

0.66

UA

0.66

oa

0.66

ITE

0.65

lez

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.