INDEX

Explanations

numeric values and their representations

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

}")]

-0.62

">//

-0.62

RenderAtEndOf

-0.57

/*++

-0.57

inence

-0.55

indro

-0.55

writeFieldEnd

-0.53

ietal

-0.52

不就是

-0.51

 internetowa

-0.51

POSITIVE LOGITS

 pleaſure

0.77

 itſelf

0.70

 purpoſe

0.66

 defire

0.65

 greateſt

0.64

 poffible

0.62

 Jefus

0.62

IntoConstraints

0.60

 myſelf

0.59

 Chriftian

0.59

Activations Density 0.293%

numeric values and their representations

No Comments

No Known Activations