INDEX

Explanations

references to identification or ID numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

"},

-0.88

*~*~

-0.85

 Theſe

-0.85

\}\\

-0.84

".

-0.83

,\,\

-0.83

`).

-0.82

")){

-0.78

"]];

-0.78

)";

-0.77

POSITIVE LOGITS

id

1.68

Id

1.47

id

1.45

ids

1.42

 getId

1.41

ID

1.39

Id

1.31

IDs

1.25

ID

1.24

 Idris

1.22

Activations Density 0.092%

references to identification or ID numbers

No Comments

No Known Activations