INDEX

Explanations

database-related operations and statements

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

user variable identifiers

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

MigrationBuilder

-0.88

 autorytatywna

-0.84

 otomatig

-0.81

tvguidetime

-0.78

تقاوى

-0.77

uxxxx

-0.75

AddTagHelper

-0.75

 typelib

-0.73

AndEndTag

-0.72

RenderAtEndOf

-0.69

POSITIVE LOGITS

</h1>

0.38

Myself

0.34

0.33

</h4>

0.32

 Myself

0.32

 côtes

0.31

0.30

</h2>

0.30

CM

0.30

Activations Density 0.029%

database-related operations and statements

user variable identifiers

No Comments

No Known Activations