INDEX

Explanations

mentions of the word "Comm" or variations like "Commision" or "Commitment"

oai_token-act-pair · gpt-3.5-turbo

references to committees or group organizations

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

lings

-0.74

 Kubrick

-0.68

chest

-0.67

 Balk

-0.66

loo

-0.66

BuyableInstoreAndOnline

-0.65

 Piercing

-0.63

 Manz

-0.63

 Corinth

-0.63

 Cinderella

-0.62

POSITIVE LOGITS

ittee

1.21

uters

1.11

ission

1.11

otion

1.09

itted

1.09

issions

1.09

onsense

1.08

ourse

1.08

ittees

1.07

ittal

1.04

Activations Density 0.013%

mentions of the word "Comm" or variations like "Commision" or "Commitment"

references to committees or group organizations

No Comments

No Known Activations