INDEX

Explanations

terms related to reduction processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Tenggara

-0.70

resaid

-0.67

 AssemblyCompany

-0.65

 doInBackground

-0.61

bukkit

-0.59

setOnItem

-0.59

DateField

-0.59

rolid

-0.59

ribusiness

-0.59

]!='

-0.58

POSITIVE LOGITS

 redu

0.82

 REDUC

0.78

 Reduces

0.76

 Reduce

0.75

 Redu

0.75

 reductions

0.74

 dras

0.74

 Reduced

0.74

 reduction

0.73

Reduces

0.71

Activations Density 0.127%

terms related to reduction processes

No Comments

No Known Activations