INDEX

Explanations

programming keywords and terms related to state management or idle conditions

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

 MainAxisSize

-0.77

principalTable

-0.69

ſelf

-0.67

tagHelper

-0.67

 Pelop

-0.65

 doInBackground

-0.65

 lumineuse

-0.65

TagMode

-0.64

 poffe

-0.64

 greateſt

-0.63

POSITIVE LOGITS

 Stan

0.57

 jsPsych

0.55

labus

0.53

 Premiere

0.52

Joy

0.51

 Incorporated

0.50

zional

0.49

Idle

0.49

 stan

0.49

ban

0.49

Activations Density 2.811%

programming keywords and terms related to state management or idle conditions

No Comments

No Known Activations