INDEX

Explanations

sentences and clauses that involve opinions, beliefs, and reporting

oai_token-act-pair · gemini-2.0-flash

Reportedly believed

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

 AssemblyTitle

-0.74

ThroughAttribute

-0.72

المناصب

-0.69

 esternos

-0.69

enderror

-0.65

 ostavi

-0.62

 Administrativna

-0.62

HomeAsUpEnabled

-0.60

########.

-0.60

 Permalink

-0.57

POSITIVE LOGITS

 reportedly

1.46

 estimated

1.44

 believed

1.41

 alleged

1.30

 allegedly

1.27

 Reported

1.24

 rumored

1.23

supposed

1.23

estimated

1.22

 supposed

1.19

Activations Density 1.976%

sentences and clauses that involve opinions, beliefs, and reporting

Reportedly believed

No Comments

No Known Activations