INDEX

Explanations

occurrences of the word "number."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

principalColumn

-0.78

GEBURTSDATUM

-0.76

LayoutConstraint

-0.72

 internetowa

-0.70

 AssemblyProduct

-0.69

最快更新

-0.66

+#+

-0.65

gridx

-0.65

Personendaten

-0.64

dataIndex

-0.64

POSITIVE LOGITS

 several

1.15

 various

1.11

 numerous

1.04

several

0.97

various

0.96

 many

0.96

 ряда

0.95

 Several

0.95

Several

0.94

 العديد

0.91

Activations Density 0.205%

occurrences of the word "number."

No Comments

No Known Activations