INDEX

Explanations

references to personal or collective experiences

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

lists of details or descriptions

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

AccessorTable

-0.50

CROSSTALK

-0.46

 Wikiseite

-0.35

นั้น

-0.33

 memang

-0.33

 sachant

-0.33

 musst

-0.32

EDEFAULT

-0.32

 Administrativna

-0.32

 choć

-0.31

POSITIVE LOGITS

RegistryLite

0.55

rungsseite

0.50

 FormData

0.49

iania

0.48

tences

0.47

 nomination

0.47

 imagui

0.47

ils

0.47

 nominations

0.47

 Johnnie

0.47

Activations Density 0.084%

references to personal or collective experiences

lists of details or descriptions

No Comments

No Known Activations