INDEX

Explanations

specific character sequences or patterns, especially those related to mathematical or scientific notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 consultato

-0.57

WithFormat

-0.55

 <=",

-0.54

 autorytatywna

-0.53

öszi

-0.52

__*/

-0.52

awtextra

-0.50

zzleHttp

-0.50

 performance

-0.48

 <>",

-0.47

POSITIVE LOGITS

NOWLEDGE

0.61

osovo

0.57

iev

0.55

ITCHEN

0.54

inetics

0.52

 LIRE

0.50

LM

0.48

rzysz

0.48

rás

0.48

ICK

0.47

Activations Density 0.300%

specific character sequences or patterns, especially those related to mathematical or scientific notation

No Comments

No Known Activations