INDEX

Explanations

words related to driving and drivers

oai_token-act-pair · gpt-3.5-turbo

references to drivers

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

 Bulg

-0.71

oire

-0.71

phia

-0.67

riched

-0.67

elligence

-0.65

 Shap

-0.65

Nau

-0.64

 Vault

-0.63

quest

-0.62

+=

-0.62

POSITIVE LOGITS

 drivers

4.00

 Drivers

3.47

 driver

2.89

drivers

2.82

 Driver

2.35

driver

2.32

 motorists

2.19

Driver

2.18

Dri

2.17

 riders

1.87

Activations Density 0.021%

words related to driving and drivers

references to drivers

No Comments

No Known Activations