INDEX

Explanations

technical terms and programming concepts related to web requests and handling

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

Code or formatting characters

np_acts-logits-general · gemini-2.0-flash

bioassay labels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

<bos>

-0.59

(:,

-0.51

 trúc

-0.45

claire

-0.44

...

-0.44

 Hicks

-0.43

AsUp

-0.43

perative

-0.43

POSITIVE LOGITS

SequentialGroup

0.99

verwijspagina

0.82

 الحره

0.81

 متعلقه

0.75

Hochspringen

0.74

 للاسماء

0.71

featureID

0.70

المناصب

0.69

."</

0.69

MessageOf

0.69

Activations Density 0.033%

technical terms and programming concepts related to web requests and handling

Code or formatting characters

bioassay labels

No Comments

No Known Activations