INDEX

Explanations

terms related to triggers in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

multer

-0.55

 Gower

-0.54

 sota

-0.53

Comté

-0.53

äsident

-0.52

דיה

-0.51

wapV

-0.50

VisualStudio

-0.50

axel

-0.50

rungsseite

-0.49

POSITIVE LOGITS

 nahilalakip

0.88

findpost

0.82

 frequency

0.76

 Frequency

0.75

Frequency

0.73

허

0.71

requency

0.70

WritableDatabase

0.70

DoubleQuotes

0.69

FREQUENCY

0.67

Activations Density 0.201%

terms related to triggers in various contexts

No Comments

No Known Activations