INDEX

Explanations

references to the term "Pokémon"

oai_token-act-pair · gpt-3.5-turbo

mentions of the Pokémon franchise and its related content

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

iffe

-0.85

)=(

-0.73

rikes

-0.73

perial

-0.70

outer

-0.69

ijk

-0.68

¿½

-0.68

cens

-0.67

bush

-0.67

ickson

-0.67

POSITIVE LOGITS

Dex

0.95

athlon

0.86

 pokemon

0.86

 Pokemon

0.84

 PokÃ©mon

0.83

PokÃ©mon

0.82

 PokÃ©

0.80

 Trainer

0.79

Pokemon

0.79

 Pikachu

0.77

Activations Density 0.026%

references to the term "Pokémon"

mentions of the Pokémon franchise and its related content

No Comments

No Known Activations