INDEX

Explanations

references to advancement or improvement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UVWXYZ

-0.90



-0.87

 Jurí

-0.86

RetentionPolicy

-0.84

MLLoader

-0.83

 giuri

-0.80

 varandra

-0.79

 archivio

-0.76

 ctypes

-0.75

 LoginForm

-0.74

POSITIVE LOGITS

 progress

1.56

 PROGRESS

1.49

 Progress

1.40

PROGRESS

1.35

Progress

1.33

progress

1.32

 progression

1.17

 progresses

1.16

 progressed

1.15

 progressing

1.10

Activations Density 0.083%

references to advancement or improvement

No Comments

No Known Activations