INDEX

Explanations

references and citations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-1.05

InjectAttribute

-0.99

Personensuche

-0.91

principalColumn

-0.90

LookAnd

-0.87

 OFDb

-0.87

parsedMessage

-0.84

ftagPool

-0.84

Xna

-0.83

SequentialGroup

-0.82

POSITIVE LOGITS

 below

1.13

 also

1.08

below

0.85

 http

0.84

 above

0.83

 note

0.83

 discussion

0.83

www

0.81

also

0.81

 Figure

0.77

Activations Density 0.283%

references and citations in the text

No Comments

No Known Activations