INDEX

Explanations

elements related to data presentation and categorization in research findings

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

Text formatting: bold, italics, highlighting

np_acts-logits-general · gemini-2.0-flash

textual emphasis and color

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Datuak

-0.69

principalColumn

-0.64

imageio

-0.58

glTex

-0.53

DOCTYPE

-0.49

يمي

-0.46

KATH

-0.46

Uninitialized

-0.46

 }}"></

-0.46

 EconPapers

-0.46

POSITIVE LOGITS

 highlighted

1.71

 underlined

1.59

 highlight

1.56

 highlighting

1.47

 Highlight

1.39

 bold

1.38

 underline

1.37

 highlights

1.37

highlighted

1.36

 emphasis

1.33

Activations Density 0.469%

elements related to data presentation and categorization in research findings

Text formatting: bold, italics, highlighting

textual emphasis and color

No Comments

No Known Activations