INDEX

Explanations

keywords related to regulations and laws

oai_token-act-pair · gpt-3.5-turbo

terms related to regulation and oversight 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Lenin

-0.78

DragonMagazine

-0.78

thia

-0.76

 Strateg

-0.69

Dad

-0.69

Plot

-0.69

Rand

-0.67

Shin

-0.66

Keefe

-0.66

ħĭ

-0.66

POSITIVE LOGITS

 regulating

1.09

 interstate

1.08

 allowable

1.00

 commercial

0.97

 federally

0.96

how

0.96

 handling

0.88

 permitting

0.88

 permissible

0.88

 workplace

0.88

Activations Density 0.305%

keywords related to regulations and laws

terms related to regulation and oversight in various contexts

No Comments

No Known Activations