INDEX

Explanations

occurrences of the term "param" in various contexts, likely indicating parameter definitions or descriptions in code

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

function parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 defensively

-0.39

 __('

-0.39

 visually

-0.39

::$_

-0.39

isEmail

-0.37

InputBorder

-0.36

าศ

-0.36

htra

-0.35

 asyncio

-0.35

Def

-0.34

POSITIVE LOGITS

param

1.18

Param

0.69

 param

0.68

usercontent

0.65

 Param

0.63

PARAM

0.61

bibfield

0.61

AndEndTag

0.57

params

0.57

parm

0.55

Activations Density 0.005%

occurrences of the term "param" in various contexts, likely indicating parameter definitions or descriptions in code

function parameters

No Comments

No Known Activations