INDEX

Explanations

references to studies and systematic reviews in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 defaultstate

-0.83

ThroughAttribute

-0.80

 Monfieur

-0.77

 kasarigan

-0.74

parsedMessage

-0.72

AndEndTag

-0.71

 itſelf

-0.71

 ddelweddau

-0.70

 wireType

-0.70

LookAnd

-0.68

POSITIVE LOGITS

${

0.65

${

0.55

Enlaces

0.46

onded

0.44

(${

0.44

<sup>

0.44

zeß

0.43

preventDefault

0.42

 chistes

0.42

anz

0.42

Activations Density 0.874%

references to studies and systematic reviews in a research context

No Comments

No Known Activations