INDEX

Explanations

phrases related to statistical significance and research findings

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

[word] + "results" or "detected" or "visible"

np_acts-logits-general · gemini-2.0-flash

test results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enumi

-0.59

 يتيمه

-0.58

IMPORTED

-0.53

 Bioaccumulative

-0.51

 متعلقه

-0.47

Bioaccumulative

-0.47

\{\\

-0.46

since

-0.44

BeginInit

-0.44

endphp

-0.44

POSITIVE LOGITS

 test

0.77

 tests

0.77

stest

0.72

 Test

0.72

 when

0.72

rimo

0.69

 Tests

0.68

 testé

0.68

Tests

0.65

 теста

0.65

Activations Density 1.073%

phrases related to statistical significance and research findings

[word] + "results" or "detected" or "visible"

test results

No Comments

No Known Activations