INDEX

Explanations

legal terms and references related to procedures and advice

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

<eos>

-0.59

 թվական

-0.54

was

-0.47

bras

-0.46

ib

-0.46

bern

-0.46

Fen

-0.45

Gson

-0.44

 static

-0.44

POSITIVE LOGITS

LookAnd

0.89

FunctionFlags

0.80

 autorytatywna

0.77

rawDesc

0.75

WriteTagHelper

0.73

 ExecuteAsync

0.73

новниш

0.70



0.68

arithmic

0.67

🏾

0.65

Activations Density 0.398%

legal terms and references related to procedures and advice

No Comments

No Known Activations