INDEX

Explanations

references to the term "Pokémon"

oai_token-act-pair · gpt-3.5-turbo

references to Pokémon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

perial

-0.83

rikes

-0.75

ijk

-0.73

ubb

-0.72

olar

-0.70

raught

-0.70

ogenous

-0.70

ickson

-0.69

akin

-0.69

ils

-0.69

POSITIVE LOGITS

PokÃ©mon

1.20

 PokÃ©mon

1.16

 pokemon

1.12

Pokemon

1.08

 Pokemon

1.05

Dex

1.01

 Pikachu

1.00

 PokÃ©

0.98

Magikarp

0.95

PokÃ©

0.86

Activations Density 0.009%

references to the term "Pokémon"

references to Pokémon

No Comments

No Known Activations