INDEX

Explanations

references to rules or guidelines

oai_token-act-pair · gpt-3.5-turbo

references to rules and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ience

-0.85

issance

-0.77

 experien

-0.76

ienced

-0.75

riel

-0.74

igated

-0.73

ONSORED

-0.70

itate

-0.69

 Hots

-0.69

apest

-0.68

POSITIVE LOGITS

 governing

1.17

breakers

1.10

 lawy

1.02

book

1.02

breaker

1.01

books

1.00

 Enforcement

0.99

 violations

0.95

 prohibiting

0.95

 regulating

0.95

Activations Density 0.027%

references to rules or guidelines

references to rules and regulations

No Comments

No Known Activations