INDEX

Explanations

generalizations or quality descriptors of situations or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

httphttps

-0.72

DebuggerNonUser

-0.69

+#+#

-0.63

INOS

-0.62

はじめに

-0.61

Décès

-0.60

GraphicsUnit

-0.59

addPreferredGap

-0.58

webElementGuid

-0.58

endorff

-0.58

POSITIVE LOGITS

 geral

0.67

 overall

0.67

 miscellaneous

0.66

Miscellaneous

0.61

overall

0.60

 allgemein

0.60

 general

0.59

 generally

0.59

 Miscell

0.58

 generale

0.58

Activations Density 0.173%

generalizations or quality descriptors of situations or items

No Comments

No Known Activations