INDEX

Explanations

references to nodes and their relationships in data structures

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

Code, math, or non-English tokens

np_acts-logits-general · gemini-2.0-flash

code and mathematical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 protoimpl

-0.57

 ISNI

-0.50

SafeAreaView

-0.48

},

-0.47

:],

-0.47

 dAtA

-0.47

TagMode

-0.47

]._

-0.46

 ""),

-0.46

POSITIVE LOGITS

 nltk

0.69

 désol

0.64

Transcripción

0.62

PathParam

0.61

yarnpkg

0.60

లాలు

0.60

LayoutConstraint

0.60

 semangat

0.60

 végétale

0.59

NameValuePair

0.59

Activations Density 0.498%

references to nodes and their relationships in data structures

Code, math, or non-English tokens

code and mathematical notation

No Comments

No Known Activations