INDEX

Explanations

proper nouns related to various individuals and entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names related to sports and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

abase

-0.81

atsu

-0.67

agara

-0.67

INO

-0.61

ward

-0.61

 kindred

-0.61

hips

-0.60

issan

-0.60

cliffe

-0.58

lyak

-0.58

POSITIVE LOGITS

monary

0.69

Desk

0.68

 Pelicans

0.67

çİĭ

0.61

etus

0.58

rences

0.57

ratulations

0.56

 Claw

0.56

 Brawl

0.54

 Nights

0.53

Activations Density 0.486%

proper nouns related to various individuals and entities

proper nouns and names related to sports and entertainment

No Comments

No Known Activations