INDEX

Explanations

terms related to preparation and predefined setups

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

words with pre prefix

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

tanleria

-0.68

MessageOf

-0.67

bootstrapcdn

-0.65

Clik

-0.63

 nakalista

-0.59

 JLabel

-0.58

onOptions

-0.57

IGENCE

-0.54

SBATCH

-0.53

StructEnd

-0.53

POSITIVE LOGITS

Pre

0.77

PRE

0.75

PRE

0.73

Pre

0.73

pre

0.69

pre

0.67

 preseason

0.64

 Pree

0.64

Preheat

0.60

预

0.59

Activations Density 0.030%

terms related to preparation and predefined setups

words with pre prefix

No Comments

No Known Activations