INDEX

Explanations

terms related to consumption, particularly in scientific or dietary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Chwiliwch

-0.89

脚注の使い方

-0.88

 referenties

-0.85

 صوتيه

-0.84

PreferredItem

-0.80

Билгалдахарш

-0.78

 Roskov

-0.77

Kjelder

-0.77

Дереккөздер

-0.75

 otomatig

-0.73

POSITIVE LOGITS

 Consumption

0.66

 consume

0.64

 consumption

0.64

 consuming

0.60

consume

0.59

 Consume

0.55

 standard

0.54

 consumo

0.54

mo

0.53

ə

0.53

Activations Density 0.207%

terms related to consumption, particularly in scientific or dietary contexts

No Comments

No Known Activations