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

erred

-0.76

ITION

-0.73

ITAL

-0.71

orney

-0.70

ital

-0.70

ardless

-0.69

 accompl

-0.67

 intens

-0.67

 decriminal

-0.66

icial

-0.65

POSITIVE LOGITS

 Royale

0.73

osaurus

0.72

 Vault

0.70

 Utilities

0.59

uckles

0.59

 shine

0.59

release

0.58

 Digest

0.58

 Gadget

0.58

aco

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.