INDEX

Explanations

terms related to plans and strategies

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Monfieur

-1.53

 myſelf

-1.53

Efq

-1.52

 pleaſure

-1.48

 Anſ

-1.47

 Reſ

-1.41

 Majefty

-1.40

 purpoſe

-1.40

 Diſ

-1.39

 Houſe

-1.39

POSITIVE LOGITS

 plan

1.07

 plans

0.93

 Plan

0.92

<eos>

0.82

plan

0.80

0.73

 Plans

0.72

0.71

Plan

0.69

 PLAN

0.69

Activations Density 0.132%

terms related to plans and strategies

No Comments

No Known Activations