INDEX

Explanations

words related to subdivision or specific locations within a broader area

oai_token-act-pair · gpt-3.5-turbo

terms associated with subdivisions and specific structural elements related to housing and community organization

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

onest

-0.81

igr

-0.72

Ã£o

-0.71

 cushion

-0.70

aer

-0.70

boxing

-0.70

mus

-0.70

gas

-0.68

gio

-0.67

anger

-0.67

POSITIVE LOGITS

cffff

0.87

CLASSIFIED

0.85

illac

0.81

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.78

ynthesis

0.77

vernment

0.74

 mathemat

0.71

seq

0.69

govtrack

0.69

ccoli

0.69

Activations Density 0.033%

words related to subdivision or specific locations within a broader area

terms associated with subdivisions and specific structural elements related to housing and community organization

No Comments

No Known Activations