INDEX

Explanations

references to sentences and their lengths within a judicial context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

первых

-0.85

icoot

-0.76

ientôt

-0.75

 guère

-0.71

laquo

-0.71

dolu

-0.70

NUMX

-0.70

 disponibilités

-0.69

 nicio

-0.67

resaid

-0.67

POSITIVE LOGITS

 sentences

1.57

 sentence

1.51

 Sentence

1.47

 Sentences

1.34

Sentence

1.27

sentence

1.16

sentences

1.16

 Cune

0.94

 sentenced

0.93

 frase

0.88

Activations Density 0.015%

references to sentences and their lengths within a judicial context

No Comments

No Known Activations