INDEX

Explanations

phrases related to avoiding spoilers

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

spoilers or avoiding spoilers

np_acts-logits-general · gemini-2.0-flash

want to avoid or not

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 nakalista

-0.64

OnAdd

-0.63

+#+#

-0.59

URLException

-0.58

himo

-0.57

skraft

-0.56

 provar

-0.56

 <>",

-0.55

Numerology

-0.52

corer

-0.52

POSITIVE LOGITS

 spoilers

1.82

 spoiler

1.77

 Spoilers

1.55

 Spoiler

1.53

 spoil

1.53

spoiler

1.52

 SPOILERS

1.42

Spoiler

1.39

spo

1.39

 SPOILER

1.39

Activations Density 0.193%

phrases related to avoiding spoilers

spoilers or avoiding spoilers

want to avoid or not

No Comments

No Known Activations