INDEX

Explanations

lines of code or programming constructs related to variable assignments and increment operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.68

 Edited

-0.58

 Scranton

-0.57

 AspNetCore

-0.57

edited

-0.56

 handwritten

-0.55

feitura

-0.55

 Srinagar

-0.55

 createState

-0.54

 Pyrr

-0.53

POSITIVE LOGITS

hasMoreElements

0.58

 فريبيس

0.57

setopt

0.49

elemField

0.48

#+#

0.48

ImageContext

0.47

اریخ

0.47

urlpatterns

0.45

MigrationBuilder

0.44

yargs

0.44

Activations Density 0.398%

lines of code or programming constructs related to variable assignments and increment operations

No Comments

No Known Activations