INDEX

Explanations

names of urban areas and biological terms related to animals or creatures, specifically in the context of a specific franchise

oai_token-act-pair · gpt-3.5-turbo

references to various fictional creatures, specifically Pokémon and their characteristics

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

 guiActiveUn

-1.04

enegger

-0.83

SPONSORED

-0.81

 actionGroup

-0.78

EngineDebug

-0.77

owship

-0.75

 staffed

-0.71

 perf

-0.71

 Bohem

-0.71

Ans

-0.69

POSITIVE LOGITS

 PokÃ©

1.24

 Pikachu

1.23

 PokÃ©mon

1.08

Dex

1.07

PokÃ©mon

1.04

 Pokemon

1.02

Pokemon

0.92

 Misty

0.90

 Fairy

0.89

 Bowser

0.89

Activations Density 0.105%

names of urban areas and biological terms related to animals or creatures, specifically in the context of a specific franchise

references to various fictional creatures, specifically Pokémon and their characteristics

No Comments

No Known Activations