INDEX

Explanations

terms related to statistical analysis and medical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Ricardo

-0.74

 Tacitus

-0.71

man

-0.70

 strdup

-0.70

CAV

-0.67

磐

-0.65

ErrorResponse

-0.65

ecap

-0.63

zeitige

-0.62

 Unsupported

-0.62

POSITIVE LOGITS

rungsseite

1.07

 للاسماء

1.07

 python

1.00

 Python

0.98

Datuak

0.95

%)$

0.92

Py

0.91

PyObject

0.87

 pyramids

0.87

 Piper

0.86

Activations Density 0.639%

terms related to statistical analysis and medical terminology

No Comments

No Known Activations