INDEX

Explanations

significant or noteworthy aspects related to change and new developments

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

original sentence, unusual site, random page

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

the neuron activates on salient content words (non-function tokens like nouns, verbs, and adjectives) that carry the main meaning of a sentence.

oai_token-act-pair · gpt-5-mini

Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Negative Logits

RenderAtEndOf

-0.58

 kasarigan

-0.51

 Administrativna

-0.48

jdź

-0.41

BufferException

-0.40

 виправивши

-0.37

 counter

-0.36

setDisabled

-0.36

counter

-0.35

 StatefulWidget

-0.35

POSITIVE LOGITS

bootstrapcdn

0.59

WriteAttribute

0.54

CppMethod

0.49

UserScript

0.43

 незавершена

0.43

RTLI

0.42

Numerade

0.42

Tikang

0.42

Staff

0.42

 AssemblyCulture

0.40

Activations Density 0.044%

significant or noteworthy aspects related to change and new developments

original sentence, unusual site, random page

the neuron activates on salient content words (non-function tokens like nouns, verbs, and adjectives) that carry the main meaning of a sentence.

No Known Activations

significant or noteworthy aspects related to change and new developments

original sentence, unusual site, random page

the neuron activates on salient content words (non-function tokens like nouns, verbs, and adjectives) that carry the main meaning of a sentence.

No Known Activations