INDEX

Explanations

language related to personal finance and credit

oai_token-act-pair · gemini-2.0-flash

terms related to credit and loans

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

line

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

IFrame

Link

Negative Logits

 صوتيه

-0.73

opedia

-0.69

OPSIS

-0.67

Bibliograf

-0.66

UrlResolution

-0.64

findpost

-0.63

 intptr

-0.62

Personendaten

-0.61

 onOptions

-0.60

msgid

-0.59

POSITIVE LOGITS

 line

0.73

 Line

0.72

Line

0.67

 facility

0.60

 LINE

0.59

 Draw

0.56

 draw

0.55

 lines

0.55

 Lines

0.54

line

0.54

Activations Density 0.841%

language related to personal finance and credit

terms related to credit and loans

line

No Known Activations