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

omore

-0.86

UME

-0.80

isode

-0.72

unciation

-0.71

poons

-0.71

usalem

-0.69

!",

-0.69

initely

-0.69

oa

-0.67

inator

-0.67

POSITIVE LOGITS

 deterior

0.71

------------------------------------------------

0.63

improve

0.63

 parap

0.60

mut

0.60

tsy

0.59

 sites

0.59

IDS

0.58

 incest

0.57

Rust

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.