INDEX

Explanations

programming constructs or elements within a coding context

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

Java/package imports

np_acts-logits-general · gemini-2.0-flash

import statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

źni

-0.55

ándor

-0.54

 promise

-0.54

AndroidJUnit

-0.53

IEnumerable

-0.53

()};

-0.52

 then

-0.51

:])

-0.51

ocry

-0.51

ruhe

-0.51

POSITIVE LOGITS

import

1.16

tagHelperRunner

0.70

 Walkover

0.58

ActionCreators

0.53

 الحره

0.53

 مرئيه

0.52

ValueStyle

0.52

public

0.51

 import

0.51

/*-

0.51

Activations Density 0.024%

programming constructs or elements within a coding context

Java/package imports

import statements

No Comments

No Known Activations