INDEX

Explanations

technical identifiers and variables in programming or scripting contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

<strong>

-0.70

 useNavigate

-0.68

<em>

-0.68

WEBPACK

-0.66

inig

-0.66

 interes

-0.66

áu

-0.62

 endregion

-0.62

<b>

-0.62

力

-0.60

POSITIVE LOGITS

rrggbb

1.01

paravant

0.80

jadinya

0.78

entraî

0.77

 gemeint

0.76

 sahiptir

0.76

 scheda

0.76

abbé

0.74

 tôt

0.74

 déput

0.73

Activations Density 0.781%

technical identifiers and variables in programming or scripting contexts

No Comments

No Known Activations