INDEX

Explanations

programming-related commands and code snippets

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

Code execution or running scripts

np_acts-logits-general · gemini-2.0-flash

run commands

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ComVisible

-0.78

 تانيه

-0.74

mybatisplus

-0.73

:+:

-0.68

WriteBarrier

-0.67

\{\\

-0.67

RegistryLite

-0.67

usermodel

-0.64

Gön

-0.63

Datuak

-0.60

POSITIVE LOGITS

run

1.32

 running

1.19

Run

1.15

 runs

1.09

run

1.08

Run

1.07

RUN

0.99

 Running

0.94

running

0.92

Running

0.92

Activations Density 0.622%

programming-related commands and code snippets

Code execution or running scripts

run commands

No Comments

No Known Activations