INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

urities

-0.76

Hok

-0.74

uyomi

-0.72

lus

-0.70

NESS

-0.67

etheless

-0.67

 ---------

-0.67

thia

-0.66

 Duchess

-0.64

atto

-0.64

POSITIVE LOGITS

ance

0.67

ances

0.66

antic

0.65

 deductions

0.61

antes

0.59

Ã¶

0.58

 breach

0.57

anthrop

0.56

stand

0.55

anka

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.