INDEX

Explanations

actions related to planning or decision-making

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

Expect

-0.55

"?>

-0.54

extField

-0.53

 numerous

-0.52

 bijna

-0.51

 çoğu

-0.51

iduous

-0.51

eraard

-0.51

often

-0.51

 countless

-0.50

POSITIVE LOGITS

 something

0.91

 someday

0.86

something

0.85

 möglichst

0.82

 revenge

0.82

adaptiveStyles

0.79

 endlich

0.71

Something

0.70

 somehow

0.70

 SOMETHING

0.70

Activations Density 0.424%

actions related to planning or decision-making

No Comments

No Known Activations