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

gencies

-0.66

 rehearsal

-0.65

 braces

-0.63

 convent

-0.63

 ropes

-0.62

VC

-0.61

 nick

-0.61

 Casting

-0.61

educ

-0.60

aya

-0.60

POSITIVE LOGITS

Footnote

0.78

lished

0.73

 millenn

0.68

NVIDIA

0.67

Accessory

0.67

DIT

0.67

Uz

0.66

TPPStreamerBot

0.65

 stru

0.64

okemon

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.