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

 decades

-0.73

 presumption

-0.64

 vanishing

-0.62

untarily

-0.62

 selves

-0.61

clusively

-0.60

bay

-0.59

parts

-0.59

 nominal

-0.59

itary

-0.58

POSITIVE LOGITS

KR

0.76

Jr

0.72

Tree

0.71

uren

0.71

Solution

0.71

ERT

0.71

 coli

0.69

urat

0.69

JV

0.69

EMS

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.