INDEX

Explanations

patterns of indentation or formatting in text

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

featureID

-0.82

 GlobalKey

-0.77

########.

-0.74

 EClass

-0.67

ThroughAttribute

-0.66

BaseResponse

-0.65

Taw

-0.65

endmodule

-0.65

fe

-0.63

UCION

-0.63

POSITIVE LOGITS

1.78

1.60

1.59

1.55

1.49

1.45

1.44

1.39

Activations Density 0.093%

patterns of indentation or formatting in text

No Comments

No Known Activations