INDEX

Explanations

occurrences of specific identifiers or codes within a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ResumeLayout

-0.65

 intptr

-0.63

invokeLater

-0.60

Filmografie

-0.55

BagConstraints

-0.54

 незавершена

-0.53

enumii

-0.50

ContentAsync

-0.50

AccessorTable

-0.48

+#+#

-0.48

POSITIVE LOGITS

hyrchwyd

0.73

 OFDb

0.62

IVENESS

0.61

onsored

0.60

mybatisplus

0.58

Hozzáférés

0.57

fört

0.55

 оригіналу

0.54

providedIn

0.54

pere

0.52

Activations Density 0.663%

occurrences of specific identifiers or codes within a structured format

No Comments

No Known Activations