INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 oxygen

-0.76

ĸļ

-0.74

oun

-0.69

 dizz

-0.68

 dynam

-0.67

 morphine

-0.67

bags

-0.65

onom

-0.64

apy

-0.64

 Morph

-0.64

POSITIVE LOGITS

arial

0.79

gomery

0.76

arding

0.74

ibilities

0.72

idth

0.72

pring

0.70

etts

0.70

ogyn

0.69

staff

0.68

arb

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.