INDEX

Explanations

escape sequences or special characters used in programming or scripting contexts

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

LaTeX code

np_acts-logits-general · gemini-2.0-flash

explaining processes

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

saw

-0.53

</em>

-0.51

maro

-0.49

ans

-0.49

cip

-0.49

far

-0.49

 user

-0.48

<sup>

-0.47

форми

-0.46

Saw

-0.45

POSITIVE LOGITS

\}\\

1.14

?\\

0.97

"\\

0.96

,\\

0.94

 doubtnut

0.93

.\\

0.92

)\\

0.92

;\\

0.92

\\

0.89

).\\

0.87

Activations Density 0.142%

escape sequences or special characters used in programming or scripting contexts

LaTeX code

explaining processes

No Comments

No Known Activations