INDEX

Explanations

labels and parameters associated with figures and diagrams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 betweenstory

-0.86

LookAnd

-0.81

новниш

-0.67

})));

-0.66

:"-"`

-0.65

ьаж

-0.62

///</

-0.62

">—

-0.61

vician

-0.61

'],'

-0.61

POSITIVE LOGITS

 BoxFit

0.65

AutoScaleMode

0.58

=\

0.57

 width

0.53

wic

0.52

 Schmer

0.52

 Width

0.49

 réglable

0.49

 getWidth

0.48

 cref

0.48

Activations Density 0.037%

labels and parameters associated with figures and diagrams

No Comments

No Known Activations