INDEX

Explanations

numerical sequences or mathematical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

دانشنامهٔ

-0.84

wwwwwwww

-0.82

frow

-0.79

 González

-0.75

UnknownFields

-0.74

../../../

-0.74

PWN

-0.71

 Juana

-0.71

spesies

-0.71

 Duckworth

-0.71

POSITIVE LOGITS

1.96

rd

1.31

1.07

iii

1.01

３

1.01

۳

0.99

 Three

0.95

३

0.95

 tercio

0.94

 THREE

0.94

Activations Density 1.021%

numerical sequences or mathematical terms

No Comments

No Known Activations