INDEX

Explanations

references to news programs and their formats

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

ViewFeatures

-0.83

expandindo

-0.59

InjectAttribute

-0.56

oa̍t

-0.55

TargetException

-0.55

QMetaType

-0.54

AddTagHelper

-0.53

 مشين

-0.53

 الرياضيه

-0.52

 Amateur

-0.51

POSITIVE LOGITS

CNN

0.76

CNN

0.72

 MSNBC

0.71

cnn

0.61

NgModule

0.61

cnn

0.58

 segmento

0.57

DllImport

0.57

 anchors

0.55

Joining

0.55

Activations Density 0.174%

references to news programs and their formats

No Comments

No Known Activations