INDEX

Explanations

terminology and concepts related to legal evidence and rules, particularly in the context of academic discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

########.

-0.97

coccus

-0.72

 Koenig

-0.72

 oocytes

-0.70

 municípios

-0.69

 география

-0.69

 vold

-0.69

anthemum

-0.68

 células

-0.67

 cellule

-0.66

POSITIVE LOGITS

 myſelf

1.34

ſelves

1.30

ſelf

1.26

 itſelf

1.26

 themſelves

1.25

 himſelf

1.24

 Conſ

1.07

 Reſ

1.05

 raiſ

1.05

 ་་

1.03

Activations Density 2.057%

terminology and concepts related to legal evidence and rules, particularly in the context of academic discussion

No Comments

No Known Activations