INDEX

Explanations

words and terms related to validation and confirmation processes, especially in the context of account management

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

Non-English text or code

np_acts-logits-general · gemini-2.0-flash

code, math, or programmatic elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

<eos>

-0.58

in

-0.57

la

-0.56

 just

-0.52

-0.51

-0.50

-0.48

de

-0.47

POSITIVE LOGITS

 itſelf

1.30

ConstraintMaker

1.24

 '\\;'

1.14

 كومونز

1.14

 Cæsar

1.10

ViewImports

1.09

RectangleBorder

1.09

IntoConstraints

1.09

 MainAxisSize

1.09

 themſelves

1.07

Activations Density 0.039%

words and terms related to validation and confirmation processes, especially in the context of account management

Non-English text or code

code, math, or programmatic elements

No Comments

No Known Activations