INDEX

Explanations

words related to court proceedings, opinions, scientific findings and apathy

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-0.44

 sfor

-0.43

 diligence

-0.43

ellites

-0.42

non

-0.40

 morm

-0.39

DebuggerStep

-0.38

Non

-0.38

tr

-0.38

aroa

-0.37

POSITIVE LOGITS

 Theſe

0.97

 Monfieur

0.92

 myſelf

0.92

 itſelf

0.89

 greateſt

0.88

Efq

0.88

 ſta

0.88

 Diſ

0.87

 Jefus

0.85

 themſelves

0.84

Activations Density 2.826%

words related to court proceedings, opinions, scientific findings and apathy

No Comments

No Known Activations