INDEX

Explanations

code segments and programming constructs related to error handling and logging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

GenerationType

-0.60

 actionMode

-0.54

ΐ

-0.50

ecznie

-0.50

 gestione

-0.49

quat

-0.47

에는

-0.47

 Gaye

-0.46

ropa

-0.45

цездатний

-0.45

POSITIVE LOGITS

 today

1.29

 currently

1.26

 сейчас

1.17

today

1.16

currently

1.15

 current

1.10

 Currently

1.10

 tonight

1.09

now

1.06

Currently

1.05

Activations Density 0.165%

code segments and programming constructs related to error handling and logging

No Comments

No Known Activations