INDEX

Explanations

URLs and references to documentation or academic papers

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

AndEndTag

-0.72

MessageOf

-0.67

 NSCoder

-0.64

 Obrador

-0.61

ModelAdmin

-0.61

يميديا

-0.59

 ddelweddau

-0.56

 otomatig

-0.56

 propOrder

-0.55

衛門

-0.54

POSITIVE LOGITS

 linkovi

0.63

endous

0.54

Prensa

0.51

Дереккөздер

0.50

0.49

 Audiodateien

0.47

 acuity

0.46

 platform

0.45

DRY

0.45

 khối

0.44

Activations Density 0.552%

URLs and references to documentation or academic papers

No Comments

No Known Activations