INDEX

Explanations

references to various biological and computational models or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

CloseOperation

-0.80

 >=",

-0.70

 المعيارى

-0.68

 valid

-0.66

+#+#

-0.64

 virtuel

-0.62

RegressionTest

-0.61

 violenza

-0.57

CodeAttribute

-0.57

Становништво

-0.57

POSITIVE LOGITS

]")]

0.65

 versa

0.61

vya

0.59

Efq

0.56

 autopsy

0.54

 clip

0.54

 AssemblyTitle

0.54

Parcelize

0.53

 intptr

0.52

 vVar

0.51

Activations Density 1.093%

references to various biological and computational models or systems

No Comments

No Known Activations