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

quo

-0.74

 Rent

-0.67

vet

-0.66

 Harden

-0.65

 Luna

-0.63

alion

-0.63

 staples

-0.62

azard

-0.61

ering

-0.61

ommel

-0.60

POSITIVE LOGITS

emphasis

0.97

lake

0.83

aka

0.74

impl

0.74

definition

0.72

excluding

0.72

except

0.72

sic

0.71

see

0.69

benef

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.