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

rates

-0.87

ipers

-0.69

rate

-0.67

strength

-0.65

rations

-0.63

ockey

-0.61

adal

-0.60

 Adamant

-0.59

ommel

-0.58

 volumes

-0.57

POSITIVE LOGITS

haw

0.86

cknow

0.76

AMY

0.75

merce

0.72

cknowled

0.71

hirt

0.68

hur

0.66

ylum

0.64

punk

0.64

irgin

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.