INDEX

Explanations

elements and symbols related to programming and scripting code

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

code or function calls

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

 smtplib

-0.54

Географи

-0.54

gemeester

-0.52

Personendaten

-0.50

RTEE

-0.50

 ब्रेकडाउन

-0.47

 TestBed

-0.45

]--;

-0.44

#+#

-0.44

Abp

-0.44

POSITIVE LOGITS

MessageState

0.51

 transcript

0.44

Tags

0.44

naie

0.42

Transcript

0.42

CAPTION

0.42

隆

0.41

ieval

0.41

 ſhall

0.41

Vent

0.40

Activations Density 0.001%

elements and symbols related to programming and scripting code

code or function calls

No Comments

No Known Activations