INDEX

Explanations

elements related to transitions and state changes in programming contexts

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

preceding "Manager", "writer", "cursor", or numbers

np_acts-logits-general · gemini-2.0-flash

technical terms and code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

+#+#

-0.63

SerializedName

-0.63

 Pingback

-0.62

 '\\;'

-0.62

GORITH

-0.60

getItemId

-0.60

 ujednoznacz

-0.59

ChatColor

-0.58

 numberOfRows

-0.58

InSection

-0.58

POSITIVE LOGITS

География

0.56

backed

0.55

Cyfeiriadau

0.52

ďaka

0.49

Erreferentziak

0.47

rój

0.45

Instance

0.44

AdapterFactory

0.43

KATH

0.43

tım

0.43

Activations Density 0.575%

elements related to transitions and state changes in programming contexts

preceding "Manager", "writer", "cursor", or numbers

technical terms and code snippets

No Comments

No Known Activations