INDEX

Explanations

words related to questions and answers

oai_token-act-pair · gemini-2.0-flash

Correctness/agreement

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 puissiez

-0.66

tahu

-0.45

 AssemblyProduct

-0.44

 dolayı

-0.44

 stället

-0.44

liputi

-0.44

lê

-0.43

estero

-0.43

 habido

-0.43

 humeur

-0.43

POSITIVE LOGITS

 Correct

0.78

 correct

0.76

sp

0.75

correct

0.70

Does

0.67

Correct

0.67

 Does

0.66

 CORRECT

0.63

Is

0.63

 corrected

0.59

Activations Density 2.573%

words related to questions and answers

Correctness/agreement

No Comments

No Known Activations