INDEX

Explanations

connective words and phrases indicating causation or conditions

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

following commas

np_acts-logits-general · gemini-2.0-flash

time reversal symmetry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 AssemblyCulture

-0.66

protoimpl

-0.64

AddTagHelper

-0.63

ſelf

-0.61

cipline

-0.58

centiles

-0.57

siasme

-0.57

 GenerationType

-0.55

siery

-0.54

 ujednoznacz

-0.54

POSITIVE LOGITS

<bos>

0.41

Hauptartikel

0.39

 makl

0.36

 high

0.36

ResumeLayout

0.35

 identity

0.35

 fore

0.35

onOptions

0.35

مراجع

0.34

…

0.34

Activations Density 0.158%

connective words and phrases indicating causation or conditions

following commas

time reversal symmetry

No Comments

No Known Activations