INDEX

Explanations

references to the Pokémon franchise

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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

perial

-0.77

ubb

-0.71

pres

-0.70

iffe

-0.70

rikes

-0.69

ndra

-0.68

pressed

-0.68

ijk

-0.67

outer

-0.67

akin

-0.66

POSITIVE LOGITS

PokÃ©mon

0.99

Dex

0.96

 pokemon

0.96

 PokÃ©mon

0.92

 Pokemon

0.92

Pokemon

0.90

 PokÃ©

0.80

Gy

0.80

 Pikachu

0.79

 Trainer

0.78

Activations Density 0.015%

references to the Pokémon franchise

references to Pokémon

No Comments

No Known Activations