INDEX

Explanations

occurrences of the letter 'n'

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

code snippets and formatting

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

uxxxx

-0.90

ReusableCell

-0.88

tagHelperRunner

-0.81

AddTagHelper

-0.79

 propOrder

-0.78

 ſind

-0.77

bootstrapcdn

-0.76



-0.76

makeConstraints

-0.76

 protoimpl

-0.75

POSITIVE LOGITS

 entire

0.40

biet

0.40

 whole

0.38

0.37

 Gottlieb

0.35

<u>

0.34

GENERIC

0.34

OCOL

0.32

Activations Density 0.028%

occurrences of the letter 'n'

code snippets and formatting

No Comments

No Known Activations