INDEX

Explanations

elements of a programming language related to structure and function definitions

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

Code, delimiters, and some non-alphanumeric characters

np_acts-logits-general · gemini-2.0-flash

code variables and symbols

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

درب

-0.46

 iprot

-0.46

mona

-0.45

tabile

-0.43

oretical

-0.42

retta

-0.42

ugin

-0.42

θυ

-0.42

떻

-0.41

iane

-0.41

POSITIVE LOGITS

2.08

1.50

=$

1.35

{$

1.35

($

1.34

/$

1.34

-$

1.32

($

1.25

://$

1.25

:$

1.25

Activations Density 0.104%

elements of a programming language related to structure and function definitions

Code, delimiters, and some non-alphanumeric characters

code variables and symbols

No Comments

No Known Activations