INDEX

Explanations

references to garages

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "garage."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.94

vironment

-0.92

uality

-0.85

ciating

-0.84

emic

-0.78

 Archdemon

-0.78

ebus

-0.76

inel

-0.75

 Marketable

-0.75

tics

-0.74

POSITIVE LOGITS

 garage

1.14

 door

0.86

door

0.85

 Garage

0.82

 doors

0.81

chair

0.78

 attic

0.77

stairs

0.75

 dealership

0.74

 Door

0.72

Activations Density 0.011%

references to garages

occurrences of the word "garage."

No Comments

No Known Activations