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

 Ascension

-0.69

 Hunts

-0.65

SELECT

-0.64

 Archangel

-0.64

 Mage

-0.62

IENT

-0.62

 Sentinel

-0.62

 Brief

-0.61

ORTS

-0.60

 Soldier

-0.60

POSITIVE LOGITS

peak

0.84

onsense

0.79

govtrack

0.73

ono

0.73

ensical

0.73

cribed

0.72

 dismant

0.70

ymes

0.69

 rewritten

0.68

eme

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.