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

 affirm

-0.75

iated

-0.73

 bour

-0.72

 authent

-0.69

 unmarked

-0.68

 Spiegel

-0.68

 zones

-0.68

 blank

-0.67

querade

-0.66

 dots

-0.65

POSITIVE LOGITS

 WEEK

0.77

 DRAG

0.74

 Animation

0.73

Accessory

0.72

roller

0.72

selection

0.71

orneys

0.71

 Traff

0.70

videos

0.70

SpaceEngineers

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.