INDEX

Explanations

references to mathematical notations and operations related to functions and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 möjligt

-0.69

 Zjednoc

-0.66

prepareStatement

-0.63

 Tolstoy

-0.61

ondra

-0.60

 tails

-0.59

 douceur

-0.59

 giudi

-0.58

cils

-0.57

 Ortsteil

-0.57

POSITIVE LOGITS

 Gund

1.09

Bronnen

1.06

GS

0.98

0.95

 kasarigan

0.93

gs

0.91

GSC

0.91

GES

0.90

Gad

0.88

GSA

0.88

Activations Density 1.304%

references to mathematical notations and operations related to functions and variables

No Comments

No Known Activations