INDEX

Explanations

numbers or numerical representations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

kef

-0.59

MigrationBuilder

-0.56

WebServlet

-0.55

HideFlags

-0.55

CodedInputStream

-0.54

HasForeignKey

-0.53

TLDR

-0.53

唆

-0.52

interopRequire

-0.52

 EconPapers

-0.50

POSITIVE LOGITS

SequentialGroup

0.61

CloseOperation

0.61

TintMode

0.59

INSEE

0.56

querque

0.53

AntiForgeryToken

0.53

basicConfig

0.52

 NgModule

0.52

 שוליים

0.51

Activations Density 0.148%

numbers or numerical representations within the text

No Comments

No Known Activations