INDEX

Explanations

questions, especially those starting with "what" or "how"

oai_token-act-pair · gemini-2.0-flash

questions about frameworks and specifications

np_token-act-pair-logits · gpt-4o-mini

what

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

رشف

-0.52

elemField

-0.51

databind

-0.47

mlı

-0.45

 PartialEq

-0.44

NewUrlParser

-0.44

BufferException

-0.43

diging

-0.42

🟤

-0.41

POA

-0.41

POSITIVE LOGITS

 propOrder

0.85

 transfieras

0.77

 programs

0.66

setVerticalGroup

0.64

 type

0.64

GEBURTSDATUM

0.63

 they

0.60

Portale

0.59

enterOuterAlt

0.58

RenderAtEndOf

0.58

Activations Density 2.713%

questions, especially those starting with "what" or "how"

questions about frameworks and specifications

what

No Comments

No Known Activations