INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

birds

-0.82

species

-0.76

dogs

-0.75

dog

-0.75

bird

-0.71

esting

-0.69

arning

-0.68

ingly

-0.68

athering

-0.67

chest

-0.66

POSITIVE LOGITS

 Redux

0.70

 arresting

0.64

 Mumbai

0.62

ihar

0.62

aults

0.61

oho

0.60

ocide

0.60

 fortun

0.60

onz

0.59

*/(

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.