INDEX

Explanations

statements related to opinions or positions

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

taking a stance or position

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

 sánchez

-0.49

 otomatig

-0.49

 fantasi

-0.47

IsMutable

-0.44

 esternos

-0.43

 fernández

-0.42

 bonjour

-0.41

 autoradio

-0.41

 permu

-0.41

 inspirations

-0.41

POSITIVE LOGITS

 stance

0.98

 position

0.86

 Stellung

0.84

 Position

0.84

position

0.81

 POSITION

0.74

 posición

0.73

 posição

0.73

 stances

0.72

Position

0.71

Activations Density 0.027%

statements related to opinions or positions

taking a stance or position

No Comments

No Known Activations

statements related to opinions or positions

taking a stance or position

No Comments

No Known Activations