INDEX

Explanations

words related to locks and lockouts

oai_token-act-pair · gpt-3.5-turbo

terms related to restrictions or blockades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

comed

-0.71

chio

-0.70

 Palin

-0.66

 plotting

-0.65

 Fried

-0.64

 Beir

-0.63

 Romantic

-0.63

Winged

-0.63

plot

-0.63

von

-0.62

POSITIVE LOGITS

 locks

2.59

 lockout

2.19

locks

1.84

 squat

1.70

 lockdown

1.69

 barric

1.57

 locking

1.53

 lock

1.31

 squats

1.28

locking

1.23

Activations Density 0.030%

words related to locks and lockouts

terms related to restrictions or blockades

No Comments

No Known Activations