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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itives

-0.74

issance

-0.71

ptions

-0.71

 dwarves

-0.69

 Firefly

-0.67

glers

-0.67

 retribution

-0.66

 Execution

-0.65

 Ghostbusters

-0.63

force

-0.63

POSITIVE LOGITS

 plur

0.71

 mortg

0.71

opt

0.67

opath

0.67

ijn

0.65

otrop

0.62

Grant

0.62

kar

0.61

ribe

0.60

ysis

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.