INDEX

Explanations

topics related to control and authority within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTS

-0.85

IRUS

-0.80

✭✭

-0.79

NUMX

-0.76

 NSCoder

-0.72

UserScript

-0.71

ölkerung

-0.70

theless

-0.70

adecimal

-0.70

(;;)

-0.69

POSITIVE LOGITS

to

0.91

0.88

),

0.84

0.81

was

0.79

is

0.77

are

0.76

 will

0.75

or

0.73

Activations Density 2.890%

topics related to control and authority within various contexts

No Comments

No Known Activations