INDEX

Explanations

terms related to needs, qualities, and measurements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RTLR

-0.59

bootstrapcdn

-0.58

 snippetHide

-0.58

tvguidetime

-0.57

GEBURTSDATUM

-0.55

 disambiguazione

-0.54

Bakgrunnsstoff

-0.53

TryDecodeAsNil

-0.52

Autoritní

-0.51

Зноскі

-0.51

POSITIVE LOGITS

<%@

0.33

ⓧ

0.29

0.28

signed

0.28

explique

0.28

manned

0.28

InSection

0.27

 immune

0.27

 пред

0.27

ً

0.27

Activations Density 0.044%

terms related to needs, qualities, and measurements in various contexts

No Comments

No Known Activations