INDEX

Explanations

references to enterprise and its associated concepts across different contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ttemberg

-0.84

 onOptions

-0.76

MethodManager

-0.74

 Paglinawan

-0.73

mybatisplus

-0.70

slidesPer

-0.70

 dépos

-0.69

CHLOR

-0.69

𝘯

-0.68

KGB

-0.66

POSITIVE LOGITS

któ

1.01

 Erskine

0.93

 Mercier

0.90

Ã

0.87

>-->

0.87

 Biscuit

0.87

 Fiore

0.86

}';

0.86

]));

0.85

;">

0.84

Activations Density 0.200%

references to enterprise and its associated concepts across different contexts

No Comments

No Known Activations