INDEX

Explanations

definitions or mentions of the term "Neutron"

oai_token-act-pair · gpt-3.5-turbo

references to specific types of Pokémon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

hips

-0.81

loo

-0.78

 bearer

-0.68

DOWN

-0.67

 injection

-0.67

inately

-0.67

REAM

-0.63

 buzzing

-0.61

ENSE

-0.60

 dissolved

-0.60

POSITIVE LOGITS

arest

1.32

verend

1.20

braska

1.18

olithic

1.17

umann

1.14

uron

1.12

oliberal

1.09

utral

1.06

cker

1.06

arthed

1.01

Activations Density 0.024%

definitions or mentions of the term "Neutron"

references to specific types of Pokémon

No Comments

No Known Activations