INDEX

Explanations

programming syntax and function definitions

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

Code-related abbreviations

np_acts-logits-general · gemini-2.0-flash

img-fan-pod-aut-point-error-rate-hdr

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ScopeManager

-0.52

ulon

-0.51

лтамалар

-0.49

HasOne

-0.48

 casualties

-0.47

HON

-0.45

LLocation

-0.44

Formik

-0.44

 drive

-0.43

ql

-0.42

POSITIVE LOGITS

 Theſe

0.43

 grego

0.40

OGND

0.38

]--;

0.36

 sirena

0.36

fromnode

0.35

simpleType

0.35

 fidé

0.35

canestro

0.35

PerformLayout

0.34

Activations Density 0.419%

programming syntax and function definitions

Code-related abbreviations

img-fan-pod-aut-point-error-rate-hdr

No Comments

No Known Activations