INDEX

Explanations

mathematical symbols or notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

lande

-0.61

Ro

-0.59

-0.58

cia

-0.56

mil

-0.54

-0.52

ThroughAttribute

-0.51

=<?

-0.51

 core

-0.51

INCREF

-0.51

POSITIVE LOGITS

\]

0.93

↵↵

0.82

MethodManager

0.68

 chré

0.66

 مشين

0.66

 مرئيه

0.64

 wikipagina

0.60

}".

0.60

Hochspringen

0.60

 dévelo

0.59

Activations Density 0.230%

mathematical symbols or notation

No Comments

No Known Activations