INDEX

Explanations

references to specific programming libraries and software components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 traceback

-0.54

olition

-0.52

 digress

-0.50

ishw

-0.49

 administracy

-0.48

netinet

-0.48

 intro

-0.48

Ruz

-0.48

별

-0.47

ghum

-0.47

POSITIVE LOGITS

 nakalista

0.94

#+#

0.93

jspx

0.92

mybatisplus

0.85

TagMode

0.83

 nahilalakip

0.81

Personendaten

0.80

 ComVisible

0.80

tagext

0.72

%)$

0.70

Activations Density 2.698%

references to specific programming libraries and software components

No Comments

No Known Activations