INDEX

Explanations

references to technology or objects related to self-driving or autonomous systems

oai_token-act-pair · gpt-3.5-turbo

references to self-driving or autonomous technology

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

 Syndicate

-0.80

 GOODMAN

-0.77

 Flavoring

-0.76

 Ashe

-0.76

 XIII

-0.70

 Fever

-0.70

 Orchestra

-0.69

 ounces

-0.69

————————

-0.68

 arrivals

-0.66

POSITIVE LOGITS

destruct

1.27

 destruct

1.18

lect

0.81

 explanatory

0.79

uls

0.78

uded

0.77

aram

0.77

ridges

0.75

comm

0.74

imm

0.72

Activations Density 0.014%

references to technology or objects related to self-driving or autonomous systems

references to self-driving or autonomous technology

No Comments

No Known Activations