INDEX

Explanations

references to documents, copies, and presentations related to legal or administrative processes

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

words like original, copy, excerpt

np_acts-logits-general · gemini-2.0-flash

original excerpts and portions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 autorytatywna

-0.79

 createState

-0.71

 فريبيس

-0.66

})->

-0.62

منابع

-0.61

]")]

-0.58

pegno

-0.57

 acrylique

-0.57

}],

-0.56

posób

-0.56

POSITIVE LOGITS

 original

0.69

 documents

0.65

 entire

0.59

Original

0.58

 excerpts

0.56

original

0.56

 portions

0.53

 originals

0.53

全文

0.53

 originale

0.53

Activations Density 0.492%

references to documents, copies, and presentations related to legal or administrative processes

words like original, copy, excerpt

original excerpts and portions

No Comments

No Known Activations