INDEX

Explanations

instances of proper names and titles within a legal or formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ratulations

-0.93

BibitemShut

-0.89

nicity

-0.86

æa

-0.85

NameInMap

-0.82

duled

-0.82

Personendaten

-0.78

othesis

-0.76

ſtanding

-0.75

Hauptartikel

-0.75

POSITIVE LOGITS

0.54

0.50

0.47

0.46

0.45

0.44

pro

0.43

Activations Density 0.479%

instances of proper names and titles within a legal or formal context

No Comments

No Known Activations