INDEX

Explanations

terms related to authority and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ness

-0.61

tings

-0.60

lanzen

-0.60

hasNext

-0.59

toThrow

-0.59

chiato

-0.59

 Aiken

-0.59

ndel

-0.59

 Fros

-0.58

klus

-0.58

POSITIVE LOGITS

 Authority

2.09

 authority

1.99

 AUTHORITY

1.99

authority

1.98

 authorities

1.97

Authority

1.92

 Authorities

1.89

authorities

1.83

Authorities

1.65

 autorité

1.56

Activations Density 0.063%

terms related to authority and its implications

No Comments

No Known Activations