INDEX

Explanations

references to minimum thresholds or quantities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 مشين

-1.04

 Theſe

-0.85

Efq

-0.81

 Fergus

-0.77

 uſed

-0.76

XLV

-0.76

例句

-0.76

 Jefus

-0.76

ⓧ

-0.76

 demografica

-0.74

POSITIVE LOGITS

 least

0.97

jmniej

0.82

Least

0.71

 almeno

0.69

 atleast

0.67

 wenigstens

0.65

 LEAST

0.65

 setidaknya

0.65

least

0.64

 Least

0.64

Activations Density 0.057%

references to minimum thresholds or quantities in various contexts

No Comments

No Known Activations