INDEX

Explanations

technical terms and names in an academic or programming context

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

 trattano

-0.50

ZING

-0.49

legi

-0.48

 living

-0.45

deu

-0.45

ftagPool

-0.45

 shock

-0.42

—

-0.41

OGA

-0.41

Архівовано

-0.41

POSITIVE LOGITS

 betweenstory

0.90

 kasarigan

0.84

 termica

0.67

########.

0.67

 pinulongan

0.65

kháu

0.65

 تانيه

0.63

rowser

0.62

 mxArray

0.62

Tikang

0.61

Activations Density 0.254%

technical terms and names in an academic or programming context

No Comments

No Known Activations