INDEX

Explanations

mentions of the word "ham"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Brice

-0.74

 JADX

-0.72

NewUrlParser

-0.71

 circle

-0.71

sumoto

-0.70

UnknownFieldSet

-0.68

aarrggbb

-0.67

fjspx

-0.66

gi

-0.63

 thiệu

-0.63

POSITIVE LOGITS

ham

1.47

HAM

1.14

ham

0.91

hams

0.87

Ham

0.84

Ham

0.83

Gri

0.67

gri

0.67

Хьажоргаш

0.66

 substrate

0.66

Activations Density 0.068%

mentions of the word "ham"

No Comments

No Known Activations