INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Reviewer

-0.84

elligence

-0.74

named

-0.73

raught

-0.71

oidal

-0.70

thora

-0.69

ãĥĭ

-0.67

Uri

-0.67

IAS

-0.65

atre

-0.64

POSITIVE LOGITS

jri

0.67

dylib

0.60

 monog

0.60

_-_

0.60

aders

0.59

 predictions

0.58

 unavoid

0.58

 rebell

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.