INDEX

Explanations

programming functions related to encoding and decoding data

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

encoding and decoding data

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

 ſche

-0.60

 Reſ

-0.52

SequentialGroup

-0.51

isDebugEnabled

-0.49

 Houſe

-0.49

$_"

-0.48

[*]

-0.48

 arşivlendi

-0.48

 HasFactory

-0.47

\{\\

-0.47

POSITIVE LOGITS

decode

0.79

LElement

0.48

encode

0.47

 decode

0.47

Decode

0.45

Descrizione

0.44

 linguagem

0.44

ServiceModel

0.42

läufe

0.41

〖

0.40

Activations Density 0.002%

programming functions related to encoding and decoding data

encoding and decoding data

No Comments

No Known Activations