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

achus

-0.67

 antit

-0.67

 accum

-0.66

 devil

-0.65

 irritating

-0.65

 sorting

-0.65

 ruining

-0.64

 confuse

-0.63

 annoying

-0.63

 trig

-0.63

POSITIVE LOGITS

çīĪ

0.78

sites

0.77

 PAGE

0.76

ĸļ

0.74

eteen

0.72

iterranean

0.71

jan

0.70

Notice

0.69

gerald

0.69

odcast

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.