INDEX

Explanations

references to "high" or "high quality" 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

uttgart

-0.65

QMetaType

-0.65

 voyez

-0.65

 PhpStorm

-0.62

oldest

-0.61

نگار

-0.61

 encantado

-0.61

 extranjera

-0.60

creatures

-0.59

 Réponses

-0.58

POSITIVE LOGITS

 high

3.57

high

3.22

 High

3.13

High

3.12

 HIGH

2.79

HIGH

2.68

高

2.23

low

2.04

 higher

1.93

 tinggi

1.89

Activations Density 0.136%

references to "high" or "high quality" in various contexts

No Comments

No Known Activations