INDEX

Explanations

references to the term "base" in various contexts

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

"base" followed by specific nouns

np_acts-logits-general · gemini-2.0-flash

base prefix technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Italijani

-0.60

 nakalista

-0.55

 createSlice

-0.54

 basadas

-0.53

AddTagHelper

-0.53

isamment

-0.52

 basis

-0.52

bcryptjs

-0.52

 يتيمه

-0.51

 tombé

-0.50

POSITIVE LOGITS

camp

0.92

 camp

0.75

camps

0.71

plate

0.71

lines

0.69

 Camp

0.67

BALL

0.67

Camp

0.66

ClientSize

0.66

ments

0.61

Activations Density 0.098%

references to the term "base" in various contexts

"base" followed by specific nouns

base prefix technical terms

No Comments

No Known Activations