INDEX

Explanations

terms related to specific medical procedures or conditions

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

Preceding words/tokens before "context"

np_acts-logits-general · gemini-2.0-flash

strategic initiatives

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

ValueStyle

-0.57

 Utilizing

-0.55

Personensuche

-0.51

:✨

-0.51

 congru

-0.50

 semif

-0.50

 utilizing

-0.48

 Utilize

-0.48

isl

-0.48

 voli

-0.47

POSITIVE LOGITS

 sonriente

0.95

 sonriendo

0.85

 informaciones

0.83

 sobretudo

0.81

 sonrisa

0.77

 misiones

0.77

 embarazadas

0.77

 llorando

0.74

 estatua

0.74

 sorpresas

0.74

Activations Density 0.261%

terms related to specific medical procedures or conditions

Preceding words/tokens before "context"

strategic initiatives

No Comments

No Known Activations