INDEX

Explanations

programming syntax related to task definitions in build automation

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

enderror

-0.75

AddTagHelper

-0.66

MLLoader

-0.63

twimg

-0.60

ValueStyle

-0.59

StoreMessageInfo

-0.57

 &___

-0.55

 FormData

-0.51

 dAtA

-0.51

ContentAsync

-0.51

POSITIVE LOGITS

 pleaſure

0.39

 Engle

0.37

['

0.35

 estés

0.35

LEGGI

0.34

:['

0.34

complexType

0.33

 McCullough

0.31

SequentialGroup

0.31

 parroquia

0.31

Activations Density 0.003%

programming syntax related to task definitions in build automation

<start_of_turn> user

No Comments

No Known Activations