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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sacrific

-0.69

 whispers

-0.68

 maze

-0.66

!!

-0.63

]+

-0.63

 screams

-0.62

 intrig

-0.62

wip

-0.61

 twists

-0.61

??

-0.60

POSITIVE LOGITS

utenberg

0.76

prototype

0.75

ingham

0.68

XL

0.68

gart

0.67

acco

0.64

Factor

0.64

origin

0.64

 Action

0.63

aurus

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.