INDEX

Explanations

references to PokÃ©mon characters or related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of Pokémon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.83

creen

-0.81

aging

-0.78

rikes

-0.76

ittens

-0.75

rib

-0.74

kef

-0.74

isen

-0.73

unta

-0.73

ipping

-0.73

POSITIVE LOGITS

 Puzz

0.77

 Dian

0.71

PokÃ©mon

0.68

 PokÃ©mon

0.68

arthed

0.65

ãĥķ

0.64

 "$:/

0.64

PokÃ©

0.63

alities

0.62

ITION

0.61

Activations Density 0.024%

references to PokÃ©mon characters or related terms

mentions of Pokémon

No Comments

No Known Activations