INDEX

Explanations

mentions of the name "Leo," particularly with high activation values

oai_token-act-pair · gpt-3.5-turbo

references to the character Leo from "Titanic" and associated topics

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

pmwiki

-0.92

geon

-0.88

erness

-0.87

FactoryReloaded

-0.84

spe

-0.84

Ô

-0.81

geons

-0.78

NetMessage

-0.77

TPPStreamerBot

-0.76

adesh

-0.75

POSITIVE LOGITS

 Burnett

0.77

Pis

0.72

enary

0.72

 tuna

0.69

 XIII

0.69

Var

0.66

Fi

0.65

 Forward

0.64

Vie

0.63

 Skywalker

0.63

Activations Density 0.101%

mentions of the name "Leo," particularly with high activation values

references to the character Leo from "Titanic" and associated topics

No Comments

No Known Activations