INDEX

Explanations

code-related variable assignments and manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

بوابة

-0.58

</tfoot>

-0.57

 ioutil

-0.50

@[+][

-0.49

PyExc

-0.48

__*/

-0.47

VolleyError

-0.47

SequentialGroup

-0.47

 stmt

-0.47

PTT

-0.46

POSITIVE LOGITS

 transfieras

0.61

StructEnd

0.58

 PLWABN

0.57

 FontWeight

0.54

 Winaray

0.54

SharedDtor

0.53

Identyfik

0.53

Ngb

0.53

 intptr

0.51

EndInit

0.50

Activations Density 0.197%

code-related variable assignments and manipulations

No Comments

No Known Activations