INDEX

Explanations

elements that describe attributes or characteristics of items, often in a structured format

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

description: or "summon"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

principalColumn

-0.46

锈钢

-0.45

muerzo

-0.43

 سكانية

-0.42

 plazos

-0.42

 neighbourhoods

-0.41

 besos

-0.40

 artificiales

-0.40

 rotación

-0.38

 equalled

-0.38

POSITIVE LOGITS

 This

0.66

This

0.63

 this

0.57

这是一个

0.52

 Provide

0.52

 Provides

0.50

Provide

0.50

Provides

0.48

resents

0.48

 aceasta

0.48

Activations Density 0.010%

elements that describe attributes or characteristics of items, often in a structured format

description: or "summon"

No Known Activations