INDEX

Explanations

terms related to technical identifiers or indexing in data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

awtextra

-1.02

VersionUID

-0.86

 Holt

-0.85

Holt

-0.85

Notae

-0.82

 holotype

-0.79

исленность

-0.79

 Geraldine

-0.78

Jang

-0.77

 AttributeSet

-0.76

POSITIVE LOGITS

WHE

0.88

WHE

0.83

Whe

0.81

 Wheaton

0.81

gonna

0.80

 Wheeler

0.80

whe

0.78

(/\

0.77

Gonna

0.75

kafka

0.72

Activations Density 0.367%

terms related to technical identifiers or indexing in data structures

No Comments

No Known Activations