INDEX

Explanations

sequences of underscores, which may indicate formatting or structural elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

)");

-1.05

).</

-1.03

)";

-0.91

"]];

-0.86

"):

-0.85

)”.

-0.85

)*/

-0.83

":

-0.82

."));

-0.80

]";

-0.79

POSITIVE LOGITS

__

3.61

__

2.52

(__

1.89

(__

1.83

.__

1.82

 (!__

1.72

'__

1.68

'__

1.64

"__

1.63

___

1.63

Activations Density 0.064%

sequences of underscores, which may indicate formatting or structural elements in code

No Comments

No Known Activations