INDEX

Explanations

common stem and suffix patterns in Portuguese and Spanish

oai_token-act-pair · gpt-3.5-turbo

terms related to sociological or demographic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

KING

-0.67

BSD

-0.65

Reloaded

-0.57

Background

-0.57

KY

-0.55

Previous

-0.54

FA

-0.54

FUL

-0.54

NEW

-0.53

HAM

-0.52

POSITIVE LOGITS

antam

0.75

enez

0.73

Ã³

0.71

unci

0.68

Ã¡s

0.67

heter

0.67

ultan

0.66

itud

0.66

ande

0.64

Ort

0.64

Activations Density 0.101%

common stem and suffix patterns in Portuguese and Spanish

terms related to sociological or demographic concepts

No Comments

No Known Activations