INDEX

Explanations

blocks of code or structured programming elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

endmodule

-0.83

(?,

-0.80

RegressionTest

-0.74

 MatDialog

-0.73

+</

-0.72

<",

-0.71

 Doyle

-0.69

 fuse

-0.69

featureID

-0.69

PreferredItem

-0.67

POSITIVE LOGITS

1.69

1.33

1.30

1.20

1.19

1.18

1.16

1.13

1.12

Activations Density 0.000%

blocks of code or structured programming elements

No Comments

No Known Activations