INDEX

Explanations

numerical values and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 initComponents

-0.79

httphttps

-0.78

 disponibilités

-0.77

Odkazy

-0.77

zkopf

-0.75

 CYTHON

-0.73

 Sandberg

-0.73

PSO

-0.72

gasus

-0.71

 estekak

-0.70

POSITIVE LOGITS

 Stepan

0.66

 Aras

0.63

 Bree

0.63

TNA

0.61

 Escribe

0.61

UNRELATED

0.61

ülete

0.60

 Digi

0.60

 Aiden

0.60

joda

0.60

Activations Density 0.130%

numerical values and comparisons

No Comments

No Known Activations