INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

avorite

-0.83

ãĥĺ

-0.75

nep

-0.70

 destro

-0.68

 perspect

-0.68

ãĤĵ

-0.67

 Kenyan

-0.67

 Croat

-0.66

 confir

-0.63

 cone

-0.63

POSITIVE LOGITS

engers

0.68

ozo

0.68

gebra

0.66

 Enough

0.61

addin

0.61

lamm

0.61

FC

0.60

 Instruction

0.60

ology

0.59

itudes

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.