INDEX

Explanations

terms related to programming concepts and variable handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.81

multer

-0.62

ঙ

-0.54

InSection

-0.54

zin

-0.54

 BorderRadius

-0.52

KEYCODE

-0.52

pic

-0.51

 présidenti

-0.51

 Henn

-0.51

POSITIVE LOGITS

archiviato

0.73

 الحره

0.67

alised

0.66

ProcessEvent

0.66

 محفوظة

0.62

 Bourgoin

0.60

 виправивши

0.56

*/}

0.56

neté

0.56

uride

0.55

Activations Density 0.081%

terms related to programming concepts and variable handling

No Comments

No Known Activations