INDEX

Explanations

elements related to definitions and properties in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

<eos>

-0.65

UnusedPrivate

-0.50

ben

-0.48

-0.47

pat

-0.46

 eind

-0.46

Ben

-0.46

-0.45

POSITIVE LOGITS

AnchorStyles

0.94

.")]

0.92

katapos

0.90

 autorytatywna

0.89

</caption>

0.87

 BoxFit

0.87

aarrggbb

0.85

setVerticalGroup

0.85

."));

0.84

seamnă

0.84

Activations Density 0.292%

elements related to definitions and properties in a technical context

No Comments

No Known Activations