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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imore

-0.81

 guiActiveUnfocused

-0.69

Ħ¢

-0.67

roup

-0.65

 trave

-0.64

minster

-0.62

roid

-0.61

instance

-0.61

oyal

-0.61

acre

-0.60

POSITIVE LOGITS

pointer

0.84

 Izan

0.71

atos

0.68

kos

0.63

tl

0.62

 dracon

0.62

hunt

0.60

izing

0.60

kr

0.60

 giveaway

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.