INDEX

Explanations

structured output and error reporting in programming or scripting contexts

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

Code or configuration snippets

np_acts-logits-general · gemini-2.0-flash

SQL LIMIT clauses and printf formatting

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>

-0.66

-0.65

-0.64

for

-0.56

↵↵

-0.55

-0.52

the

-0.51

 both

-0.49

all

-0.49

POSITIVE LOGITS

IntoConstraints

1.39

rungsseite

1.27

ConstraintMaker

1.15

 surla

1.14

SBATCH

1.14

 AssemblyVersion

1.06

 estekak

1.06

 BorderRadius

1.03

 ویکی‌پدیا

1.03

EDEFAULT

1.02

Activations Density 0.126%

structured output and error reporting in programming or scripting contexts

Code or configuration snippets

SQL LIMIT clauses and printf formatting

No Comments

No Known Activations