INDEX

Explanations

occurrences of import statements in code

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

module imports and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

DoubleQuotes

-0.53

verwijspagina

-0.52

="@+

-0.52

MigrationBuilder

-0.50

 ejus

-0.49

 ModelExpression

-0.49

 enfans

-0.49

StoryboardSegue

-0.49

AddTagHelper

-0.48

+#+#

-0.48

POSITIVE LOGITS

stdc

0.43

حياته

0.41

⤹

0.39

Born

0.38

tovers

0.36

PyExc

0.36

 disponibilités

0.34

Portail

0.34

ENSIONS

0.33

ftagPool

0.33

Activations Density 0.001%

occurrences of import statements in code

module imports and definitions

No Comments

No Known Activations