INDEX

Explanations

code snippets, especially PHP code and related error messages

oai_token-act-pair · gemini-2.0-flash

code-related terminology

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

Code snippets

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

 AssemblyCulture

-0.56

[]:

-0.55

 insuffisamment

-0.54

-0.52

 resultCode

-0.51

OrBuilder

-0.47

WebControls

-0.47

careous

-0.46

 joão

-0.44

gradable

-0.44

POSITIVE LOGITS

aarrggbb

0.60

 BoxDecoration

0.58

šem

0.56

 OnTriggerEnter

0.54

ArrowToggle

0.54

ph

0.52

PreferredItem

0.51

 QWidget

0.50

stdc

0.50

LLocation

0.50

Activations Density 0.751%

code snippets, especially PHP code and related error messages

code-related terminology

Code snippets

No Comments

No Known Activations