INDEX

Explanations

dialogue and quotations in the text

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

WithIOException

-0.68

ionato

-0.67

WriteTagHelper

-0.65

}(),

-0.61

</caption>

-0.60

)}]{

-0.59

PyExc

-0.59

—

-0.59

 AssemblyCulture

-0.58

/*",

-0.58

POSITIVE LOGITS

Yeah

1.00

Oh

0.95

Exactly

0.90

What

0.89

That

0.88

 Exactly

0.87

 Yeah

0.85

And

0.84

Oh

0.80

You

0.79

Activations Density 0.126%

dialogue and quotations in the text

No Comments

No Known Activations