INDEX

Explanations

sentences discussing products and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

OrNil

-0.77

IntoConstraints

-0.76

 дописавши

-0.75

dersfield

-0.74

 onCancelled

-0.71

 Signalez

-0.69

Hozzáférés

-0.69

Архівовано

-0.68

endpush

-0.64

DockStyle

-0.64

POSITIVE LOGITS

 original

0.49

 그는

0.48

 ایشان

0.47

original

0.47

gore

0.46

 Coates

0.46

 archive

0.45

 그의

0.45

 ornate

0.45

 beautifully

0.44

Activations Density 0.059%

sentences discussing products and their features

No Comments

No Known Activations