INDEX

Explanations

references to classification or categorization within a structured context, such as matrices or data sets

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 jsPsych

-0.72

TagMode

-0.63

SourceChecksum

-0.63

']")

-0.60

 ""],

-0.56

RegressionTest

-0.55

 resourceCulture

-0.53

rédients

-0.53

})));

-0.52

 >=",

-0.52

POSITIVE LOGITS

GraphicsUnit

0.64

וויק

0.59

getSystemService

0.58

TintMode

0.56

urium

0.54

Ẫ

0.53

entibus

0.52

ddots

0.51

Ibid

0.51

Hozzáférés

0.51

Activations Density 5.531%

references to classification or categorization within a structured context, such as matrices or data sets

No Comments

No Known Activations