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

sson

-0.84

Iw

-0.76

 dotted

-0.70

mate

-0.69

 Icelandic

-0.66

 streak

-0.64

imately

-0.62

 Turks

-0.61

 iPod

-0.61

 umbrella

-0.60

POSITIVE LOGITS

conf

0.79

Development

0.73

ICO

0.72

 Nanto

0.69

atro

0.68

isine

0.68

proc

0.67

ases

0.67

 Crisis

0.64

atin

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.