INDEX

Explanations

occurrences of specific verbs and phrases related to measurement and data analysis

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

reading measurements

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

makedirs

-0.36

 BorderSide

-0.36

VersionUID

-0.35

 mani

-0.34

Personendaten

-0.33

 demo

-0.32

neu

-0.31

rho

-0.31

dor

-0.30

 سرا

-0.30

POSITIVE LOGITS

 reading

0.87

 readings

0.80

 read

0.79

reading

0.77

 lectura

0.77

읽

0.75

 Readings

0.75

 readout

0.74

Reading

0.73

 Reading

0.72

Activations Density 0.122%

occurrences of specific verbs and phrases related to measurement and data analysis

reading measurements

No Comments

No Known Activations