INDEX

Explanations

the presence of specific markers indicating the start of a new section or significant content in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Personendaten

-1.20

EndGlobalSection

-1.18

Personensuche

-0.97

hyrchwyd

-0.93

ThroughAttribute

-0.89

LookAnd

-0.84

 propOrder

-0.82

 resourceCulture

-0.82

AccessorTable

-0.82

AsUp

-0.80

POSITIVE LOGITS

⎪

0.56

]][

0.47

 rowspan

0.45

lawan

0.45

 zaraz

0.44

 гра

0.44

 Stairs

0.44

 Reverse

0.43

✳

0.43

⎧

0.42

Activations Density 0.028%

the presence of specific markers indicating the start of a new section or significant content in a document

No Comments

No Known Activations