INDEX

Explanations

references to licenses and their associated terms

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

words indicating release

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Absch

-0.39

ugh

-0.38

 geboten

-0.36

 wasted

-0.35

 Bingham

-0.34

 Bezir

-0.34

#+#

-0.33

vención

-0.33

 Dobson

-0.33

präch

-0.32

POSITIVE LOGITS

 release

1.70

 Release

1.64

release

1.59

Release

1.57

 RELEASE

1.52

 releases

1.45

 releasing

1.41

 Releases

1.41

Releases

1.34

 released

1.33

Activations Density 0.011%

references to licenses and their associated terms

words indicating release

No Comments

No Known Activations