INDEX

Explanations

terms related to medical and legal procedural contexts

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

resave

-0.55

alba

-0.52

 Malo

-0.50

atier

-0.48

Mio

-0.47

Noi

-0.46

Mas

-0.46

Mas

-0.45

 Wikispecies

-0.45

 nakalista

-0.44

POSITIVE LOGITS

ment

1.89

ments

1.75

MENT

1.75

mento

1.49

ement

1.47

 ment

1.45

Ment

1.45

menta

1.41

MENTS

1.39

men

1.34

Activations Density 0.329%

terms related to medical and legal procedural contexts

No Comments

No Known Activations