INDEX

Explanations

indicators of file updates and changes in programming contexts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

-0.56

-0.50

<eos>

-0.49

ill

-0.49

pro

-0.48

 asam

-0.46

ire

-0.46

re

-0.46

in

-0.45

POSITIVE LOGITS

 hObject

1.53

 purpoſe

1.10

InputBorder

1.10

 itſelf

1.05

 pleaſure

1.05

 myſelf

1.05

 eventdata

1.05

 ſtate

1.03

 houſe

1.03

 perſon

0.97

Activations Density 0.000%

indicators of file updates and changes in programming contexts

No Comments

No Known Activations