INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

unal

-0.82

chy

-0.74

yip

-0.73

eco

-0.72

peat

-0.70

felt

-0.66

ieth

-0.65

ynchronous

-0.65

velop

-0.64

eem

-0.63

POSITIVE LOGITS

 axes

0.80

 resil

0.72

 veter

0.70

 directories

0.69

asion

0.67

ives

0.67

 advoc

0.65

 experien

0.65

 bindings

0.64

atherine

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.