INDEX

Explanations

significant numerical values or flags indicating important information

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

code syntax

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

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

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.99

SequentialGroup

-0.99

MessageOf

-0.98

GEBURTSDATUM

-0.98

RenderAtEndOf

-0.96

 AssemblyCompany

-0.95

ConstraintMaker

-0.94

IntoConstraints

-0.94

IUrlHelper

-0.93

bootstrapcdn

-0.92

POSITIVE LOGITS

0.42

↵↵

0.42

’

0.40

0.38

↵↵↵

0.37

 sometimes

0.35

↵

0.35

 often

0.35

Activations Density 0.000%

significant numerical values or flags indicating important information

code syntax

No Comments

No Known Activations