INDEX

Explanations

references to "inner" and "outer" concepts, particularly in scientific or technical contexts

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

"inner" or "outer" followed by a noun

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 transfieras

-0.45

tagHelperRunner

-0.44

 pinulongan

-0.41

addContainerGap

-0.40

("")]

-0.36

 snippetHide

-0.35

 Cryst

-0.35

️

-0.35

?>/

-0.35

setcounter

-0.34

POSITIVE LOGITS

 Outer

0.80

 Inner

0.79

 inner

0.73

Inner

0.72

Outer

0.71

 INNER

0.70

inner

0.69

outer

0.66

 OUTER

0.65

 outer

0.65

Activations Density 0.082%

references to "inner" and "outer" concepts, particularly in scientific or technical contexts

"inner" or "outer" followed by a noun

No Comments

No Known Activations