INDEX

Explanations

words and phrases that describe positive outcomes from medical treatments, personal hardships and athletic performance

oai_token-act-pair · gemini-2.0-flash

references to specific concepts or identifiers

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

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

 this

-1.41

this

-1.00

 этого

-0.84

 questa

-0.78

這個

-0.77

 resourceCulture

-0.75

 THIS

-0.75

the

-0.74

 dieses

-0.73

 этой

-0.73

POSITIVE LOGITS

 These

0.65

These

0.60

เหล

0.59

这些

0.53

ándolos

0.52

これらの

0.52

這些

0.50

どれも

0.48

 Olympedia

0.47

ModelSerializer

0.47

Activations Density 5.827%

words and phrases that describe positive outcomes from medical treatments, personal hardships and athletic performance

references to specific concepts or identifiers

No Comments

No Known Activations