INDEX

Explanations

references to the concept of learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 learning

-0.71

__',

-0.57

 виправивши

-0.57

cestors

-0.53

NameInMap

-0.53

 confirming

-0.52

 Theſe

-0.51

$")

-0.50

 educativas

-0.50

ồm

-0.49

POSITIVE LOGITS

 transfieras

0.75

TagMode

0.65

CreateModel

0.63

gonic

0.60

jspx

0.60

ResponseWriter

0.60

يميديا

0.60

 InputDecoration

0.60

 sklearn

0.58

 AdapterView

0.58

Activations Density 0.029%

references to the concept of learning

No Comments

No Known Activations