INDEX

Explanations

phrases related to drivers or driving

oai_token-act-pair · gpt-3.5-turbo

references to drivers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ropolitan

-0.78

 Flavoring

-0.76

imaru

-0.75

chan

-0.74

asia

-0.72

 Coast

-0.69

inion

-0.69

 Territories

-0.69

iry

-0.69

 Brother

-0.69

POSITIVE LOGITS

 drivers

1.33

driver

1.09

 Drivers

1.08

 driver

1.06

drivers

0.92

driving

0.84

 pige

0.83

 bees

0.83

 licenses

0.83

 driving

0.80

Activations Density 0.011%

phrases related to drivers or driving

references to drivers in various contexts

No Comments

No Known Activations