INDEX

Explanations

messages or alerts related to errors and success notifications

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

rungsseite

-0.62

:],

-0.52

حوالہ

-0.52

 ?>">

-0.51

')):

-0.50

"):

-0.47

_,

-0.46

qua

-0.45

"],

-0.45

 seis

-0.44

POSITIVE LOGITS

 resourceCulture

0.78

 Sorry

0.78

 sorry

0.72

NameInMap

0.72

 Assyrian

0.71

 Jefus

0.71

 Cæsar

0.71

sorry

0.70

Tikang

0.70

Sorry

0.70

Activations Density 0.058%

messages or alerts related to errors and success notifications

No Comments

No Known Activations