INDEX

Explanations

references to "heap" in various contexts

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

heap praise or pile

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Jeografia

-0.68

RegressionTest

-0.58

 propOrder

-0.54

 Italijanski

-0.51

adaptiveStyles

-0.51

WindowConstants

-0.51

transQ

-0.50

UnusedPrivate

-0.50

pexpr

-0.49

DataContract

-0.48

POSITIVE LOGITS

 heap

1.84

 heaps

1.53

 Heap

1.42

heap

1.35

Heap

1.32

 heaped

1.31

 heapq

1.00

HEAP

0.91

 pile

0.81

 piles

0.77

Activations Density 0.004%

references to "heap" in various contexts

heap praise or pile

No Comments

No Known Activations