INDEX

Explanations

terms related to compliance and violations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-1.00

StoryboardSegue

-0.91

BeginContext

-0.89

UnknownFieldSet

-0.83

stdc

-0.82

TestingModule

-0.81

 Alembic

-0.78

 CreateTagHelper

-0.76

 GenerationType

-0.75

Tazama

-0.75

POSITIVE LOGITS

 compliance

2.94

 Compliance

2.67

compliance

2.61

Compliance

2.50

 compliant

2.10

 comply

1.98

PLIANCE

1.93

compliant

1.84

 complying

1.79

 complies

1.72

Activations Density 0.105%

terms related to compliance and violations

No Comments

No Known Activations