INDEX

Explanations

references to the letter "F" in various contexts, likely indicating a focus on names, variables, or classifications associated with that letter

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

Token "F" followed by a digit or non-alphabetic character

np_acts-logits-general · gemini-2.0-flash

F followed by tokens like `ella`, `od`, `ari`, `earing`

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

Rüyada

-0.54

 AssemblyCulture

-0.52

unc

-0.50

Referanser

-0.46

ειτουργ

-0.46

 CYTHON

-0.45

مصادر

-0.44

</tfoot>

-0.44

معلومات

-0.44

brin

-0.43

POSITIVE LOGITS

DockStyle

0.59

readystatechange

0.58

httphttps

0.57

 createSlice

0.56

UniformLocation

0.53

Federal

0.52

 Federal

0.51

 Yourself

0.51

 tournage

0.49

 ogen

0.49

Activations Density 0.234%

references to the letter "F" in various contexts, likely indicating a focus on names, variables, or classifications associated with that letter

Token "F" followed by a digit or non-alphabetic character

F followed by tokens like `ella`, `od`, `ari`, `earing`

No Comments

No Known Activations

references to the letter "F" in various contexts, likely indicating a focus on names, variables, or classifications associated with that letter

Token "F" followed by a digit or non-alphabetic character

F followed by tokens like `ella`, `od`, `ari`, `earing`

No Comments

No Known Activations