INDEX

Explanations

mention of instructions and details regarding processes, particularly in technical contexts

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

Code snippets or step-by-step instructions

np_acts-logits-general · gemini-2.0-flash

lists and instructions

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

queryInterface

-0.64

migrationBuilder

-0.54

dafx

-0.51

 defaultstate

-0.50

 snippetHide

-0.47

terase

-0.46

WebMethod

-0.46

CPtr

-0.46

 BoxDecoration

-0.44

Hochspringen

-0.44

POSITIVE LOGITS

toprule

0.41

zyka

0.39

ofstd

0.38

rungsseite

0.37

 ExecuteAsync

0.36

leyebilirsiniz

0.36

 Branch

0.36

 ramas

0.35

 referencias

0.34

 Kessler

0.34

Activations Density 0.907%

mention of instructions and details regarding processes, particularly in technical contexts

Code snippets or step-by-step instructions

lists and instructions

No Comments

No Known Activations