INDEX

Explanations

terms related to permits and privileges

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

tvguidetime

-0.73

audiovisuel

-0.70

twimg

-0.66

 cref

-0.64

noinspection

-0.63

uegos

-0.63

 AssemblyCulture

-0.62

NewLabel

-0.60

ceğ

-0.59

VENUE

-0.59

POSITIVE LOGITS

 Plan

0.81

 PLAN

0.72

Plan

0.69

 plan

0.68

 privilege

0.65

 propOrder

0.65

ther

0.64

 permission

0.64

tione

0.59

 permit

0.59

Activations Density 0.106%

terms related to permits and privileges

No Comments

No Known Activations