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

Interstitial

-0.95

Ire

-0.69

ife

-0.69

gress

-0.66

apy

-0.65

ioxide

-0.65

WAYS

-0.64

Else

-0.63

 Habit

-0.63

Experience

-0.62

POSITIVE LOGITS

wrapper

0.72

antry

0.69

eto

0.67

twe

0.65

ega

0.61

nos

0.57

 bastard

0.56

prop

0.56

majority

0.56

iring

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.