INDEX

Explanations

sequence and structure of location-specific information

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

AndEndTag

-0.76

 snippetHide

-0.73

 intptr

-0.71

featureID

-0.70

WithIOException

-0.69

RegressionTest

-0.69

parsedMessage

-0.67

tagHelperRunner

-0.65

:+:

-0.65

 actionBar

-0.62

POSITIVE LOGITS

 exit

0.80

 turn

0.75

 heading

0.74

 exiting

0.72

 turning

0.71

exit

0.66

Exiting

0.65

 uscire

0.65

 towards

0.65

 entrance

0.63

Activations Density 0.181%

sequence and structure of location-specific information

No Comments

No Known Activations