INDEX

Explanations

terms related to obtaining results or solutions in mathematical contexts

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

 Wikimedijinoj

-0.77

rrggbb

-0.76

UnsafeEnabled

-0.75

posedge

-0.73

WebServlet

-0.73

ReusableCell

-0.72

 doInBackground

-0.71

 resourceCulture

-0.70

enumi

-0.67

mybatisplus

-0.67

POSITIVE LOGITS

 additionally

0.80

 again

0.72

 also

0.65

 instead

0.65

 successively

0.63

 separately

0.63

 сначала

0.62

 forthwith

0.61

 another

0.60

 subsequently

0.59

Activations Density 0.968%

terms related to obtaining results or solutions in mathematical contexts

No Comments

No Known Activations