INDEX

Explanations

references to news organizations or media outlets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.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

SequentialGroup

-0.92

 Chwiliwch

-0.63

DebuggerNonUser

-0.57

 <<<<<<<<<<<<<<

-0.54

memoized

-0.54

CrossRef

-0.52

 الاطلاع

-0.52

 Extragalactic

-0.52

ClientSize

-0.50

擔

-0.49

POSITIVE LOGITS

WriteTagHelper

0.79

WriteBarrier

0.56

λέον

0.53

 كومونز

0.52

atrième

0.52

iseksi

0.51

 décisions

0.49

 deschis

0.49

 खरीदा

0.48

ponses

0.48

Activations Density 0.014%

references to news organizations or media outlets

No Comments

No Known Activations