INDEX

Explanations

auxillary verbs and prepositions that indicate relationships or actions

oai_token-act-pair · gemini-2.0-flash

see

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enderror

-0.56

 habari

-0.52

 BoxDecoration

-0.52

WithIOException

-0.49

ANDUM

-0.49

findpost

-0.46

protoimpl

-0.42

 XCTest

-0.42

enumi

-0.42

enumii

-0.42

POSITIVE LOGITS

see

2.31

see

1.93

See

1.85

 sees

1.84

See

1.81

 seeing

1.66

SEE

1.58

SEE

1.40

sees

1.38

seeing

1.34

Activations Density 2.422%

auxillary verbs and prepositions that indicate relationships or actions

see

No Comments

No Known Activations