INDEX

Explanations

references to programming functions and their behaviors

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

when certain phrases are likely

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

HtmlAttribute

-0.58

internalType

-0.56

ValueStyle

-0.55

 يتيمه

-0.52

 Diſ

-0.50

WriteTagHelper

-0.50

MLLoader

-0.50

 initComponents

-0.49

parsedMessage

-0.49

aarrggbb

-0.48

POSITIVE LOGITS

 IFTT

0.41

alogie

0.41

thâu

0.40

Pe

0.35

ODES

0.34

 simplifié

0.34

 then

0.34

 SDLK

0.34

My

0.33

Pan

0.32

Activations Density 0.158%

references to programming functions and their behaviors

when certain phrases are likely

No Comments

No Known Activations