INDEX

Explanations

segments of code or technical notations, though no strong activations exist

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

yntaxException

-1.14

 betweenstory

-1.11

 propOrder

-1.02

########.

-1.01

QMetaType

-0.98

Efq

-0.94

GEBURTSDATUM

-0.93

AsUp

-0.93

 doInBackground

-0.92

 nakalista

-0.92

POSITIVE LOGITS

<eos>

0.75

includegraphics

0.73

↵↵

0.68

↵

0.59

0.54

↵↵↵↵

0.52

0.50

0.49

↵↵↵

0.48

$\

0.48

Activations Density 0.002%

segments of code or technical notations, though no strong activations exist

No Comments

No Known Activations