INDEX

Explanations

terms related to leadership and guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Sampson

-0.82

 ***/

-0.80

uxxxx

-0.78

 Samir

-0.73

 mattresses

-0.72

 THOMPSON

-0.72

 Somerville

-0.71

ornis

-0.71

ildes

-0.71

 Burgers

-0.70

POSITIVE LOGITS

Leads

1.59

 lead

1.56

 leads

1.54

 Lead

1.52

 Leads

1.49

lead

1.49

leads

1.48

 LEAD

1.48

Lead

1.42

led

1.36

Activations Density 0.072%

terms related to leadership and guidance

No Comments

No Known Activations